Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
38 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Survey of the Evolution of Language Model-Based Dialogue Systems (2311.16789v1)

Published 28 Nov 2023 in cs.CL and cs.AI

Abstract: Dialogue systems, including task-oriented_dialogue_system (TOD) and open-domain_dialogue_system (ODD), have undergone significant transformations, with language_models (LM) playing a central role. This survey delves into the historical trajectory of dialogue systems, elucidating their intricate relationship with advancements in LLMs by categorizing this evolution into four distinct stages, each marked by pivotal LM breakthroughs: 1) Early_Stage: characterized by statistical LMs, resulting in rule-based or machine-learning-driven dialogue_systems; 2) Independent development of TOD and ODD based on neural_language_models (NLM; e.g., LSTM and GRU), since NLMs lack intrinsic knowledge in their parameters; 3) fusion between different types of dialogue systems with the advert of pre-trained_language_models (PLMs), starting from the fusion between four_sub-tasks_within_TOD, and then TOD_with_ODD; and 4) current LLM-based_dialogue_system, wherein LLMs can be used to conduct TOD and ODD seamlessly. Thus, our survey provides a chronological perspective aligned with LM breakthroughs, offering a comprehensive review of state-of-the-art research outcomes. What's more, we focus on emerging topics and discuss open challenges, providing valuable insights into future directions for LLM-based_dialogue_systems. Through this exploration, we pave the way for a deeper_comprehension of the evolution, guiding future developments in LM-based dialogue_systems.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (297)
  1. H. M. et al., “Challenges in building intelligent open-domain dialog systems,” ACM Trans. Inf. Syst., 2020.
  2. Z. Z. et al., “Recent advances and challenges in task-oriented dialog systems,” SCTC, 2020.
  3. Z. L. et al., “The design and implementation of XiaoIce, an empathetic social chatbot,” CL, 2020.
  4. L. O. et al., “Training language models to follow instructions with human feedback,” 2022.
  5. H. W. et al., “Chain-of-thought prompting for responding to in-depth dialogue questions with llm,” 2023.
  6. H. Y. et al., “The factual inconsistency problem in abstractive text summarization: A survey,” 2021.
  7. A. S. et al., “Lamp: When large language models meet personalization,” 2023.
  8. L. Z. et al., “Where to go for the holidays: Towards mixed-type dialogs for clarification of user goals,” in ACL, 2022.
  9. E. H. et al., “A simple language model for task-oriented dialogue,” in NeurIPS, 2020.
  10. T. V.-K. et al., “Neural-based natural language generation in dialogue using RNN encoder-decoder with semantic aggregation,” in Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, 2017.
  11. R. A. et al., “Improving language understanding by generative pre-training,” 2018.
  12. P. F. et al., “Language models as knowledge bases?” in EMNLP, 2019.
  13. Z. Y. et al., “DIALOGPT : Large-scale generative pre-training for conversational response generation,” in ACL, 2020.
  14. W. X. Z. et al., “A survey of large language models,” 2023.
  15. B. D. G. et al., “Gus, a frame-driven dialog system,” Artificial intelligence, 1977.
  16. Y. B. et al., “A neural probabilistic language model,” in NeurIPS, 2000.
  17. M. T. et al., “Recurrent neural network based language model.” in INTERSPEECH, 2010.
  18. H. S. et al., “Long short-term memory,” Neural computation, 1997.
  19. C. K. et al., “Learning phrase representations using RNN encoder–decoder for statistical machine translation,” in EMNLP, 2014.
  20. P. B. et al., “Composite task-completion dialogue policy learning via hierarchical deep reinforcement learning,” in EMNLP, 2017.
  21. W. T.-H. et al., “A network-based end-to-end trainable task-oriented dialogue system,” in EACL, 2017.
  22. C. H. et al., “A Survey on Dialogue Systems: Recent Advances and New Frontiers,” SIGKDD Explor. Newsl., 2017.
  23. D. J. et al., “BERT: Pre-training of deep bidirectional transformers for language understanding,” in NAACL-HLT, 2019.
  24. R. A. et al., “Language models are unsupervised multitask learners,” OpenAI, 2019.
  25. L. P. et al., “Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing,” ACM Comput. Surv., 2023.
  26. B. S. et al., “PLATO: Pre-trained dialogue generation model with discrete latent variable,” in ACL, 2020.
  27. ——, “PLATO-2: Towards building an open-domain chatbot via curriculum learning,” in Findings. of ACL, 2021.
  28. R. S. et al., “Recipes for building an open-domain chatbot,” in EACL, 2021.
  29. D. A. et al., “Towards a human-like open-domain chatbot,” 2020.
  30. F. M. et al., “Pangu-bot: Efficient generative dialogue pre-training from pre-trained language model,” 2022.
  31. W. W. et al., “Plug: Pre-training for language understanding and generation,” 2022.
  32. J. K. et al., “Scaling laws for neural language models,” 2020.
  33. D. Z. et al., “GLM: General language model pretraining with autoregressive blank infilling,” in ACL, 2022.
  34. H. T. et al., “Llama: Open and efficient foundation language models,” 2023.
  35. J. Z. et al., “Glm-dialog: Noise-tolerant pre-training for knowledge-grounded dialogue generation,” 2023.
  36. W. H. et al., “Integrating pretrained language model for dialogue policy evaluation,” in ICASSP, 2022.
  37. Y. K. et al., “Recurrent neural networks for language understanding.” in INTERSPEECH, 2013.
  38. M. G. et al., “Using recurrent neural networks for slot filling in spoken language understanding,” TASLP, 2014.
  39. Y. K. et al., “Spoken language understanding using long short-term memory neural networks,” in SLT, 2014.
  40. D. H. et al., “Multi-domain joint semantic frame parsing using bi-directional RNN-LSTM,” in INTERSPEECH, 2016.
  41. B. L. et al., “Attention-based recurrent neural network models for joint intent detection and slot filling,” in INTERSPEECH, 2016.
  42. G. C.-W. et al., “Slot-gated modeling for joint slot filling and intent prediction,” in NAACL-HLT, 2018.
  43. Q. L. et al., “Dynamic fusion network for multi-domain end-to-end task-oriented dialog,” in ACL, 2020.
  44. C. Q. et al., “Bert for joint intent classification and slot filling,” 2019.
  45. G. C. et al., “Multi-lingual intent detection and slot filling in a joint bert-based model,” 2019.
  46. Q. L. et al., “A stack-propagation framework with token-level intent detection for spoken language understanding,” in EMNLP, 2019.
  47. ——, “Multi-domain spoken language understanding using domain- and task-aware parameterization,” TALLIP, 2022.
  48. G. D. et al., “Multilingual and cross-lingual intent detection from spoken data,” in EMNLP, 2021.
  49. H. M. et al., “Word-based dialog state tracking with recurrent neural networks,” in SIGDIAL, 2014.
  50. M. N. et al., “Neural belief tracker: Data-driven dialogue state tracking,” in ACL, 2017.
  51. ——, “Multi-domain dialog state tracking using recurrent neural networks,” in ACL, 2015.
  52. P. J. et al., “Dialog state tracking, a machine reading approach using memory network,” in EACL, 2017.
  53. Z. V. et al., “Global-locally self-attentive encoder for dialogue state tracking,” in ACL, 2018.
  54. W. C.-S. et al., “Transferable multi-domain state generator for task-oriented dialogue systems,” in ACL, 2019.
  55. H. J. et al., “SAS: Dialogue state tracking via slot attention and slot information sharing,” in ACL, 2020.
  56. E. M. et al., “MultiWOZ 2.1: A consolidated multi-domain dialogue dataset with state corrections and state tracking baselines,” in LREC, 2020.
  57. Z. S. et al., “Efficient context and schema fusion networks for multi-domain dialogue state tracking,” in Findings. of EMNLP, 2020.
  58. L. H. et al., “SUMBT: Slot-utterance matching for universal and scalable belief tracking,” in ACL, 2019.
  59. W. D. et al., “Fast and scalable dialogue state tracking with explicit modular decomposition,” in NAACL-HLT, 2021.
  60. Z. J. et al., “Find or classify? dual strategy for slot-value predictions on multi-domain dialog state tracking,” in *SEM, 2020.
  61. G. J. et al., “Beyond the granularity: Multi-perspective dialogue collaborative selection for dialogue state tracking,” in ACL, 2022.
  62. H. D. et al., “End-to-end neural pipeline for goal-oriented dialogue systems using GPT-2,” in ACL, 2020.
  63. P. B. et al., “Soloist: Building task bots at scale with transfer learning and machine teaching,” TACL, 2021.
  64. S. P.-H. et al., “Learning from real users: Rating dialogue success with neural networks for reinforcement learning in spoken dialogue systems,” 2015.
  65. ——, “Reward shaping with recurrent neural networks for speeding up on-line policy learning in spoken dialogue systems,” in SIGDIAL, 2015.
  66. T. R. et al., “Multi-agent task-oriented dialog policy learning with role-aware reward decomposition,” in ACL, 2020.
  67. S. P.-H. et al., “On-line active reward learning for policy optimisation in spoken dialogue systems,” in ACL, 2016.
  68. T. R. et al., “Guided dialog policy learning: Reward estimation for multi-domain task-oriented dialog,” in EMNLP, 2019.
  69. L. B. et al., “Adversarial learning of task-oriented neural dialog models,” in SIGDIAL, 2018.
  70. W. T.-H. et al., “Semantically conditioned LSTM-based natural language generation for spoken dialogue systems,” in EMNLP, 2015.
  71. F. M. et al., “Meta-learning for low-resource natural language generation in task-oriented dialogue systems,” in IJCAI, 2019.
  72. C. W. et al., “Semantically conditioned dialog response generation via hierarchical disentangled self-attention,” in ACL, 2019.
  73. P. B. et al., “Few-shot natural language generation for task-oriented dialog,” in Findings. of EMNLP, 2020.
  74. S. L. et al., “Neural responding machine for short-text conversation,” in ACL, 2015.
  75. P. P. et al., “Extending neural generative conversational model using external knowledge sources,” in EMNLP, 2018.
  76. V. O. et al., “A neural conversational model,” 2015.
  77. L. J. et al., “A persona-based neural conversation model,” in ACL, 2016.
  78. Z. S. et al., “Personalizing dialogue agents: I have a dog, do you have pets too?” in ACL, 2018.
  79. S. K. et al., “Exploring personalized neural conversational models,” in IJCAI, 2017.
  80. H. Z. et al., “Modeling topical relevance for multi-turn dialogue generation,” in IJCAI, 2020.
  81. P. Z. et al., “Keyword-guided neural conversational model,” in AAAI, 2021.
  82. M. G. et al., “A knowledge-grounded neural conversation model,” in AAAI, 2018.
  83. Z. H. et al., “Eva: An open-domain chinese dialogue system with large-scale generative pre-training,” 2021.
  84. Y. G. et al., “Eva2.0: Investigating open-domain chinese dialogue systems with large-scale pre-training,” 2022.
  85. X. J. et al., “Beyond goldfish memory: Long-term open-domain conversation,” in ACL, 2022.
  86. K. M. et al., “Internet-augmented dialogue generation,” in ACL, 2022.
  87. K. S. et al., “Blenderbot 3: a deployed conversational agent that continually learns to responsibly engage,” 2022.
  88. ——, “PLATO-XL: Exploring the large-scale pre-training of dialogue generation,” in Findings. AACL-IJCNLP, 2022.
  89. W. H. et al., “TopicRefine: Joint topic prediction and dialogue response generation for multi-turn end-to-end dialogue system,” in ICNLSP), 2022.
  90. W. Y. et al., “A large-scale chinese short-text conversation dataset,” 2020.
  91. ——, “Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots,” in ACL, 2017.
  92. R. Y. et al., “Learning to respond with deep neural networks for retrieval-based human-computer conversation system,” in SIGIR, 2016.
  93. S. W. et al., “Match-srnn: Modeling the recursive matching structure with spatial RNN,” in IJCAI, 2016.
  94. M. T. et al., “Lstm-based deep learning models for non-factoid answer selection,” 2016.
  95. Z. X. et al., “Multi-view response selection for human-computer conversation,” in EMNLP, 2016.
  96. Z. Z. et al., “Modeling multi-turn conversation with deep utterance aggregation,” in COLING, 2018.
  97. B. H. et al., “Convolutional neural network architectures for matching natural language sentences,” in NeurIPS, 2014.
  98. A. S. et al., “Learning to rank short text pairs with convolutional deep neural networks,” in SIGIR, 2015.
  99. Y. S. et al., “A latent semantic model with convolutional-pooling structure for information retrieval,” in CIKM, 2014.
  100. H. M. et al., “ConveRT: Efficient and accurate conversational representations from transformers,” in Findings. of EMNLP, 2020.
  101. E. D. et al., “Wizard of wikipedia: Knowledge-powered conversational agents,” in ICLR, 2019.
  102. J. G. et al., “Speaker-aware BERT for multi-turn response selection in retrieval-based chatbots,” in CIKM, 2020.
  103. T. W. et al., “Do response selection models really know what’s next? utterance manipulation strategies for multi-turn response selection,” in AAAI, 2021.
  104. J. L. et al., “Improving contextual language models for response retrieval in multi-turn conversation,” in SIGIR, 2020.
  105. L. Z. et al., “The world is not binary: Learning to rank with grayscale data for dialogue response selection,” in EMNLP, 2020.
  106. Y. C. et al., “Multi-hop selector network for multi-turn response selection in retrieval-based chatbots,” in EMNLP, 2019.
  107. G. X. et al., “Dialogue response ranking training with large-scale human feedback data,” in EMNLP, 2020.
  108. J. Z. et al., “Ensemblegan: Adversarial learning for retrieval-generation ensemble model on short-text conversation,” in SIGIR, 2019.
  109. Y. S. et al., “An ensemble of retrieval-based and generation-based human-computer conversation systems,” in IJCAI, 2018.
  110. Y. W. et al., “Response generation by context-aware prototype editing,” in AAAI, 2019.
  111. P. G. et al., “Exemplar encoder-decoder for neural conversation generation,” in ACL, 2018.
  112. W. J. et al., “Retrieve and refine: Improved sequence generation models for dialogue,” in SCAI Workshop, 2018.
  113. L. Y. et al., “A hybrid retrieval-generation neural conversation model,” in CIKM, 2019.
  114. Z. L. et al., “The adapter-bot: All-in-one controllable conversational model,” in AAAI, 2021.
  115. S. A. et al., “A computational approach to understanding empathy expressed in text-based mental health support,” in EMNLP, 2020.
  116. S. H. et al., “PsyQA: A Chinese dataset for generating long counseling text for mental health support,” in Findings. of ACL, 2021.
  117. X. X. et al., “Long time no see! open-domain conversation with long-term persona memory,” in Findings. of ACL, 2022.
  118. Z. H. et al., “KdConv: A Chinese multi-domain dialogue dataset towards multi-turn knowledge-driven conversation,” in ACL, 2020.
  119. B. A. et al., “COMET: Commonsense transformers for automatic knowledge graph construction,” in ACL, 2019.
  120. C. Z. et al., “HiTab: A hierarchical table dataset for question answering and natural language generation,” in ACL, 2022.
  121. S. A. et al., “VQA: visual question answering,” in ICCV, 2015.
  122. W. S. et al., “More is better: Enhancing open-domain dialogue generation via multi-source heterogeneous knowledge,” in EMNLP, 2021.
  123. L. S. et al., “TruthfulQA: Measuring how models mimic human falsehoods,” in ACL, 2022.
  124. B. P. et al., “MultiWOZ - a large-scale multi-domain Wizard-of-Oz dataset for task-oriented dialogue modelling,” in EMNLP, 2018.
  125. Z. Q. et al., “CrossWOZ: A large-scale Chinese cross-domain task-oriented dialogue dataset,” TACL, 2020.
  126. J. Z. et al., “Dialogstudio: Towards richest and most diverse unified dataset collection for conversational ai,” 2023.
  127. Z. X. et al., “UniDS: A unified dialogue system for chit-chat and task-oriented dialogues,” in DialDoc Workshop, 2022.
  128. T. X. et al., “Q-TOD: A query-driven task-oriented dialogue system,” in EMNLP, 2022.
  129. C. H. et al., “A survey on dialogue systems: Recent advances and new frontiers,” SIGKDD Explor. Newsl., 2017.
  130. Q. L. et al., “A survey on spoken language understanding: Recent advances and new frontiers,” in IJCAI, 2021, survey Track.
  131. J. L. et al., ““do you follow me?”: A survey of recent approaches in dialogue state tracking,” in SIGDIAL, 2022.
  132. K. W.-C. et al., “A survey on recent advances and challenges in reinforcement learning methods for task-oriented dialogue policy learning,” MIR, 2023.
  133. L. Y. et al., “Slot-consistent NLG for task-oriented dialogue systems with iterative rectification network,” in ACL, 2020.
  134. Y. L. et al., “Interpretable NLG for task-oriented dialogue systems with heterogeneous rendering machines,” in AAAI, 2021.
  135. B. V. et al., “Recent neural methods on dialogue state tracking for task-oriented dialogue systems: A survey,” in SIGDIAL, 2021.
  136. W. H. et al., “Learning efficient dialogue policy from demonstrations through shaping,” in ACL, 2020.
  137. H. J. et al., “Hybrid reinforcement/supervised learning of dialogue policies from fixed data sets,” CL, 2008.
  138. Z. Q. et al., “ConvLab-2: An open-source toolkit for building, evaluating, and diagnosing dialogue systems,” in ACL, 2020.
  139. H. W. et al., “Kddres: A multi-level knowledge-driven dialogue dataset for restaurant towards customized dialogue system,” 2021.
  140. C. C.-Y. et al., “Gunrock: Building a human-like social bot by leveraging large scale real user data,” Alexa prize proceedings, 2018.
  141. L. C. et al., “Towards robust personalized dialogue generation via order-insensitive representation regularization,” 2023.
  142. W. R. et al., “Retrieval-free knowledge injection through multi-document traversal for dialogue models,” in ACL, 2023.
  143. C. L. et al., “Towards robust personalized dialogue generation via order-insensitive representation regularization,” in Findings. of ACL, 2023.
  144. C. Z. et al., “A comprehensive survey on pretrained foundation models: A history from bert to chatgpt,” 2023.
  145. B. P. et al., “Godel: Large-scale pre-training for goal-directed dialog,” 2022.
  146. W. L. et al., “MOSS: end-to-end dialog system framework with modular supervision,” in AAAI, 2020.
  147. S. Y. et al., “Multi-task pre-training for plug-and-play task-oriented dialogue system,” in ACL, 2022.
  148. W. H. et al., “GALAXY: A generative pre-trained model for task-oriented dialog with semi-supervised learning and explicit policy injection,” in AAAI, 2022.
  149. H. W. et al., “Unified dialog model pre-training for task-oriented dialog understanding and generation,” in SIGIR, ser. SIGIR ’22, 2022.
  150. L. X. et al., “Gpt understands, too,” AI Open, 2023.
  151. K. J. et al., “AuGPT: Auxiliary tasks and data augmentation for end-to-end dialogue with pre-trained language models,” in NLP4ConvAI Workshop, 2021.
  152. L. M. et al., “Opera: Harmonizing task-oriented dialogs and information seeking experience,” ACM Trans. Web, 2023, just Accepted.
  153. L. Z. et al., “MinTL: Minimalist transfer learning for task-oriented dialogue systems,” in EMNLP, 2020.
  154. Y. Y. et al., “UBAR: towards fully end-to-end task-oriented dialog system with GPT-2,” in AAAI, 2021.
  155. Y. Lee, “Improving end-to-end task-oriented dialog system with a simple auxiliary task,” in Findings. of EMNLP, 2021.
  156. J. N. et al., “Recent advances in deep learning based dialogue systems: a systematic survey,” Artif. Intell. Rev., 2023.
  157. L. Q. et al., “End-to-end task-oriented dialogue: A survey of tasks, methods, and future directions,” 2023.
  158. S. K. et al., “Adding chit-chat to enhance task-oriented dialogues,” in NAACL-HLT, 2021.
  159. C. S. et al., “SalesBot: Transitioning from chit-chat to task-oriented dialogues,” in ACL, 2022.
  160. C. Z. et al., “KETOD: Knowledge-enriched task-oriented dialogue,” in Findings. of NAACL, 2022.
  161. T. Y. et al., “Fusing task-oriented and open-domain dialogues in conversational agents,” in AAAI, 2022.
  162. S. K. et al., “Retrieval augmentation reduces hallucination in conversation,” in Findings. of EMNLP, 2021.
  163. K. S. et al., “Beyond domain APIs: Task-oriented conversational modeling with unstructured knowledge access,” in SIGDIAL, 2020.
  164. G. S. et al., “HyKnow: End-to-end task-oriented dialog modeling with hybrid knowledge management,” in Findings. of ACL, 2021.
  165. N. J. et al., “Combining open domain question answering with a task-oriented dialog system,” in DialDoc Workshop), 2021.
  166. S. E. M. et al., “Can you put it all together: Evaluating conversational agents’ ability to blend skills,” in ACL, 2020.
  167. T. B. B. et al., “Language models are few-shot learners,” in NeurIPS, 2020.
  168. OpenAI, “Gpt-4 technical report,” 2023.
  169. R. T. et al., “Stanford alpaca: An instruction-following llama model,” https://github.com/tatsu-lab/stanford_alpaca, 2023.
  170. C. W.-L. et al., “Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality,” 2023.
  171. Z. A. et al., “Glm-130b: An open bilingual pre-trained model,” 2022.
  172. G. P. et al., “The refinedweb dataset for falcon llm: Outperforming curated corpora with web data, and web data only,” 2023.
  173. K. L. et al., “Mpt: Mesh pre-training with transformers for human pose and mesh reconstruction,” 2023.
  174. I. Team, “Internlm: A multilingual language model with progressively enhanced capabilities,” https://github.com/InternLM/InternLM, 2023.
  175. Y. A. et al., “Baichuan 2: Open large-scale language models,” 2023.
  176. H. T. et al., “Llama 2: Open foundation and fine-tuned chat models,” 2023.
  177. J. B. et al., “Qwen technical report,” 2023.
  178. X. Z. et al., “Sgp-tod: Building task bots effortlessly via schema-guided llm prompting,” 2023.
  179. W. X. et al., “Emotional intelligence of large language models,” 2023.
  180. M. C. et al., “Evaluating large language models trained on code,” 2021.
  181. A. Z. et al., “Agenttuning: Enabling generalized agent abilities for llms,” 2023.
  182. T. R. S. et al., “Cognitive architectures for language agents,” 2023.
  183. P. J. S. et al., “Generative agents: Interactive simulacra of human behavior,” 2023.
  184. D. J. et al., “Human or not? a gamified approach to the turing test,” 2023.
  185. J. W. et al., “Chain-of-thought prompting elicits reasoning in large language models,” 2023.
  186. P. M. et al., “Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models,” 2023.
  187. Y. D. et al., “Prompting and evaluating large language models for proactive dialogues: Clarification, target-guided, and non-collaboration,” 2023.
  188. P. W. et al., “A preliminary evaluation of chatgpt for zero-shot dialogue understanding,” 2023.
  189. H. M. et al., “ChatGPT for zero-shot dialogue state tracking: A solution or an opportunity?” in ACL, 2023.
  190. H. V. et al., “Are large language models all you need for task-oriented dialogue?” in SIGDIAL, 2023.
  191. X. Y. et al., “Prompt-based monte-carlo tree search for goal-oriented dialogue policy planning,” 2023.
  192. C. Q. et al., “Is chatgpt a general-purpose natural language processing task solver?” 2023.
  193. Y. F. et al., “Uncovering the potential of chatgpt for discourse analysis in dialogue: An empirical study,” 2023.
  194. J. H. et al., “Understanding the effectiveness of very large language models on dialog evaluation,” 2023.
  195. J. M. et al., “Simple llm prompting is state-of-the-art for robust and multilingual dialogue evaluation,” 2023.
  196. B. Y. et al., “A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity,” 2023.
  197. Z. W. et al., “Is chatgpt equipped with emotional dialogue capabilities?” 2023.
  198. H. Q. et al., “Smile: Single-turn to multi-turn inclusive language expansion via chatgpt for mental health support,” 2023.
  199. Z. Z. et al., “Building emotional support chatbots in the era of llms,” 2023.
  200. J. M. L. et al., “Chatcounselor: A large language models for mental health support,” 2023.
  201. Q. T. et al., “Characterchat: Learning towards conversational ai with personalized social support,” 2023.
  202. F. Y. et al., “Reasoning before responding: Integrating commonsense-based causality explanation for empathetic response generation,” 2023.
  203. M. F. et al., “Using linguistic cues for the automatic recognition of personality in conversation and text,” JAIR, 2007.
  204. T. Y. R. et al., “The psychological meaning of words: Liwc and computerized text analysis methods,” JLS, 2010.
  205. P. Ekman, “Universals and cultural differences in facial expressions of emotion.” in Nebraska symposium on motivation, 1971.
  206. P. Turney, “Thumbs up or thumbs down? semantic orientation applied to unsupervised classification of reviews,” in ACL, 2002.
  207. Y. D. et al., “A survey on proactive dialogue systems: Problems, methods, and prospects,” in IJCAI, 2023.
  208. H. W. et al., “Large language models as source planner for personalized knowledge-grounded dialogue,” 2023.
  209. H. C. et al., “Chatdb: Augmenting llms with databases as their symbolic memory,” 2023.
  210. L. G. et al., “Prompted llms as chatbot modules for long open-domain conversation,” 2023.
  211. W. Z. et al., “Memorybank: Enhancing large language models with long-term memory,” 2023.
  212. Q. W. et al., “Recursively summarizing enables long-term dialogue memory in large language models,” 2023.
  213. L. J. et al., “Memochat: Tuning llms to use memos for consistent long-range open-domain conversation,” 2023.
  214. C. W. et al., “Survey on factuality in large language models: Knowledge, retrieval and domain-specificity,” 2023.
  215. N. B. et al., “Evaluating large language models for document-grounded response generation in information-seeking dialogues,” 2023.
  216. L. X. et al., “Webglm: Towards an efficient web-enhanced question answering system with human preferences,” 2023.
  217. S. S. J. et al., “Wikichat: A few-shot llm-based chatbot grounded with wikipedia,” 2023.
  218. T. H. et al., “Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions,” in ACL, 2023.
  219. S. X. et al., “Search-in-the-chain: Towards accurate, credible and traceable large language models for knowledge-intensive tasks,” 2023.
  220. M. L. et al., “Api-bank: A benchmark for tool-augmented llms,” 2023.
  221. S. G. P. et al., “Gorilla: Large language model connected with massive apis,” 2023.
  222. Y. L. et al., “Taskmatrix.ai: Completing tasks by connecting foundation models with millions of apis,” 2023.
  223. M. B. P. et al., “Like hiking? you probably enjoy nature: Persona-grounded dialog with commonsense expansions,” in EMNLP, 2020.
  224. F. T. et al., “There are a thousand hamlets in a thousand people’s eyes: Enhancing knowledge-grounded dialogue with personal memory,” in ACL, 2022.
  225. Z. W. et al., “Interactive natural language processing,” 2023.
  226. K. Z. et al., “Memory-augmented llm personalization with short- and long-term memory coordination,” 2023.
  227. W. H. et al., “Tpe: Towards better compositional reasoning over conceptual tools with multi-persona collaboration,” 2023.
  228. H. L. et al., “Visual instruction tuning,” 2023.
  229. D. Z. et al., “Minigpt-4: Enhancing vision-language understanding with advanced large language models,” 2023.
  230. K. Z. et al., “Minigpt-5: Interleaved vision-and-language generation via generative vokens,” 2023.
  231. J. M. et al., “MATCH: An architecture for multimodal dialogue systems,” in ACL, 2002.
  232. L. G. et al., “A survey on multimodal dialogue systems: Recent advances and new frontiers,” in AEMCSE, 2022.
  233. L. B. et al., “Transformer-based multimodal infusion dialogue systems,” Electronics, 2022.
  234. L. L. et al., “Knowledge-aware multimodal dialogue systems,” in ACM MM, 2018.
  235. A. D. et al., “Visual dialog,” in CVPR, 2017.
  236. H. A. et al., “Audio visual scene-aware dialog,” in CVPR, 2019.
  237. S. K. et al., “Image-chat: Engaging grounded conversations,” in ACL, 2020.
  238. S. W. et al., “Openvidial 2.0: A larger-scale, open-domain dialogue generation dataset with visual contexts,” 2021.
  239. Z. Y. et al., “MMChat: Multi-modal chat dataset on social media,” in LREC, 2022.
  240. A. S. et al., “Towards building large scale multimodal domain-aware conversation systems,” in AAAI, 2018.
  241. Z. X. et al., “PhotoChat: A human-human dialogue dataset with photo sharing behavior for joint image-text modeling,” in ACL, 2021.
  242. M. Z. et al., “UniTranSeR: A unified transformer semantic representation framework for multimodal task-oriented dialog system,” in ACL, 2022.
  243. F. J. et al., “MMDialog: A large-scale multi-turn dialogue dataset towards multi-modal open-domain conversation,” in ACL, 2023.
  244. H. J. et al., “DUEL: A multi-lingual multimodal dialogue corpus for disfluency, exclamations and laughter,” in LREC, 2016.
  245. L. L. et al., “M33{}^{3}start_FLOATSUPERSCRIPT 3 end_FLOATSUPERSCRIPTit: A large-scale dataset towards multi-modal multilingual instruction tuning,” 2023.
  246. W. D. et al., “Instructblip: Towards general-purpose vision-language models with instruction tuning,” 2023.
  247. H. Z. et al., “Video-llama: An instruction-tuned audio-visual language model for video understanding,” 2023.
  248. M. M. et al., “Video-chatgpt: Towards detailed video understanding via large vision and language models,” 2023.
  249. R. G. et al., “Imagebind: One embedding space to bind them all,” 2023.
  250. G. Y. et al., “Audiotoken: Adaptation of text-conditioned diffusion models for audio-to-image generation,” 2023.
  251. J. Z. et al., “Survey of hallucination in natural language generation,” ACM Computing Surveys, 2023.
  252. L. C. et al., “Beyond factuality: A comprehensive evaluation of large language models as knowledge generators,” 2023.
  253. N. K. et al., “Large language models struggle to learn long-tail knowledge,” 2023.
  254. B. X. et al., “Improving factual consistency for knowledge-grounded dialogue systems via knowledge enhancement and alignment,” 2023.
  255. H. D. et al., “Compositionality decomposed: How do neural networks generalise?” JAIR, 2020.
  256. M. R. et al., “Sequence level training with recurrent neural networks,” in ICLR, 2016.
  257. N. L. et al., “Factuality enhanced language models for open-ended text generation,” 2023.
  258. W. Y. et al., “Generate rather than retrieve: Large language models are strong context generators,” 2023.
  259. N. F. L. et al., “Evaluating verifiability in generative search engines,” 2023.
  260. J. L. et al., “Halueval: A large-scale hallucination evaluation benchmark for large language models,” 2023.
  261. N. V. et al., “A stitch in time saves nine: Detecting and mitigating hallucinations of llms by validating low-confidence generation,” 2023.
  262. S. M. et al., “Factscore: Fine-grained atomic evaluation of factual precision in long form text generation,” 2023.
  263. T. G. et al., “Enabling large language models to generate text with citations,” 2023.
  264. L. C. et al., “X-mark: Towards lossless watermarking through lexical redundancy,” 2023.
  265. A. C. et al., “Purr: Efficiently editing language model hallucinations by denoising language model corruptions,” 2023.
  266. D. N. et al., “Neural path hunter: Reducing hallucination in dialogue systems via path grounding,” in EMNLP, 2021.
  267. W. Z. et al., “Fine-grained human feedback gives better rewards for language model training,” 2023.
  268. D. J. et al., “Recent advances towards safe, responsible, and moral dialogue systems: A survey,” 2023.
  269. B. Y. et al., “Constitutional ai: Harmlessness from ai feedback,” 2022.
  270. K. A. et al., “In conversation with artificial intelligence: aligning language models with human values,” Philosophy & Technology, 2023.
  271. I. G. et al., “Ai safety needs social scientists,” Distill, 2019.
  272. Z. Y. et al., “Linking artificial intelligence principles,” 2018.
  273. W. L. et al., “Taxonomy of risks posed by language models,” in FAccT, 2022.
  274. D. J. et al., “Cold: A benchmark for chinese offensive language detection,” in EMNLP, 2022.
  275. S. M. et al., “Social bias frames: Reasoning about social and power implications of language,” in ACL, 2020.
  276. Z. J. et al., “Towards identifying social bias in dialog systems: Framework, dataset, and benchmark,” in Findings. of EMNLP, 2022.
  277. K. H. et al., “Prosocialdialog: A prosocial backbone for conversational agents,” in EMNLP, 2022.
  278. Z. J. et al., “Rethinking machine ethics – can llms perform moral reasoning through the lens of moral theories?” 2023.
  279. W. L. et al., “KGA: A general machine unlearning framework based on knowledge gap alignment,” in ACL, 2023.
  280. M. A. et al., “Mitigating covertly unsafe text within natural language systems,” in Findings. of EMNLP, 2022.
  281. S. H. et al., “On the safety of conversational models: Taxonomy, dataset, and benchmark,” in Findings. of ACL, 2022.
  282. F. M. et al., “Social chemistry 101: Learning to reason about social and moral norms,” in EMNLP, 2020.
  283. K. H. et al., “Soda: Million-scale dialogue distillation with social commonsense contextualization,” 2022.
  284. S. H. et al., “Moraldial: A framework to train and evaluate moral dialogue systems via moral discussions,” in ACL, 2023.
  285. D. H. et al., “Aligning ai with shared human values,” 2023.
  286. X. J. et al., “Recipes for safety in open-domain chatbots,” 2020.
  287. S. T. et al., “Self-diagnosis and self-debiasing: A proposal for reducing corpus-based bias in nlp,” TACL, 2021.
  288. R. T. et al., “Lamda: Language models for dialog applications,” 2022.
  289. D. E. et al., “SafetyKit: First aid for measuring safety in open-domain conversational systems,” in ACL, 2022.
  290. R. W. et al., “Self-critique prompting with large language models for inductive instructions,” 2023.
  291. D. G. et al., “The capacity for moral self-correction in large language models,” 2023.
  292. Z. W. et al., “Self-guard: Empower the llm to safeguard itself,” 2023.
  293. B. Y. et al., “Training a helpful and harmless assistant with reinforcement learning from human feedback,” arxiv, 2022.
  294. A. A. et al., “A general language assistant as a laboratory for alignment,” arXiv], 2021.
  295. A. G. et al., “Improving alignment of dialogue agents via targeted human judgements,” 2022.
  296. S. M. et al., “Annotators with attitudes: How annotator beliefs and identities bias toxic language detection,” in NAACL, 2022.
  297. F. K. C. et al., “Does moral code have a moral code? probing delphi’s moral philosophy,” in TrustNLP Workshop, 2022.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Hongru Wang (62 papers)
  2. Lingzhi Wang (54 papers)
  3. Yiming Du (13 papers)
  4. Liang Chen (360 papers)
  5. Jingyan Zhou (16 papers)
  6. Yufei Wang (141 papers)
  7. Kam-Fai Wong (92 papers)
Citations (15)
View on Semantic Scholar