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

Hallucination Diversity-Aware Active Learning for Text Summarization (2404.01588v1)

Published 2 Apr 2024 in cs.CL, cs.AI, and cs.LG

Abstract: LLMs have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, most of these methods focus on a specific type of hallucination, e.g., entity or token errors, which limits their effectiveness in addressing various types of hallucinations exhibited in LLM outputs. To our best knowledge, in this paper we propose the first active learning framework to alleviate LLM hallucinations, reducing costly human annotations of hallucination needed. By measuring fine-grained hallucinations from errors in semantic frame, discourse and content verifiability in text summarization, we propose HAllucination Diversity-Aware Sampling (HADAS) to select diverse hallucinations for annotations in active learning for LLM finetuning. Extensive experiments on three datasets and different backbone models demonstrate advantages of our method in effectively and efficiently mitigating LLM hallucinations.

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 (56)
  1. A multitask, multilingual, multimodal evaluation of ChatGPT on reasoning, hallucination, and interactivity. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 675–718, Nusa Dua, Bali. Association for Computational Linguistics.
  2. Language models are few-shot learners. In Advances in Neural Information Processing Systems, volume 33, pages 1877–1901.
  3. Hallucinated but factual! inspecting the factuality of hallucinations in abstractive summarization. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3340–3354, Dublin, Ireland. Association for Computational Linguistics.
  4. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416.
  5. Chain-of-verification reduces hallucination in large language models. arXiv preprint arXiv:2309.11495.
  6. Active Learning for BERT: An Empirical Study. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7949–7962, Online. Association for Computational Linguistics.
  7. QAFactEval: Improved QA-based factual consistency evaluation for summarization. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2587–2601, Seattle, United States. Association for Computational Linguistics.
  8. Multi-news: a large-scale multi-document summarization dataset and abstractive hierarchical model.
  9. FactKB: Generalizable factuality evaluation using language models enhanced with factual knowledge. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 933–952, Singapore. Association for Computational Linguistics.
  10. Multi-loss weighting with coefficient of variations. In 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 1468–1477.
  11. Hallucinations in Large Multilingual Translation Models. Transactions of the Association for Computational Linguistics, 11:1500–1517.
  12. Teaching machines to read and comprehend. In NIPS, pages 1693–1701.
  13. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations.
  14. Survey of hallucination in natural language generation. ACM Comput. Surv., 55(12).
  15. Josip Jukić and Jan Snajder. 2023. Parameter-efficient language model tuning with active learning in low-resource settings. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5061–5074, Singapore. Association for Computational Linguistics.
  16. Factuality enhanced language models for open-ended text generation. Advances in Neural Information Processing Systems, 35:34586–34599.
  17. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880, Online. Association for Computational Linguistics.
  18. HaluEval: A large-scale hallucination evaluation benchmark for large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6449–6464, Singapore. Association for Computational Linguistics.
  19. Loftq: LoRA-fine-tuning-aware quantization for large language models. In The Twelfth International Conference on Learning Representations.
  20. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74–81.
  21. A token-level reference-free hallucination detection benchmark for free-form text generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6723–6737, Dublin, Ireland. Association for Computational Linguistics.
  22. SelfCheckGPT: Zero-resource black-box hallucination detection for generative large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9004–9017, Singapore. Association for Computational Linguistics.
  23. Active learning by acquiring contrastive examples. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 650–663, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  24. On faithfulness and factuality in abstractive summarization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1906–1919, Online. Association for Computational Linguistics.
  25. Self-contradictory hallucinations of large language models: Evaluation, detection and mitigation. In The Twelfth International Conference on Learning Representations.
  26. Entity-level factual consistency of abstractive text summarization. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2727–2733, Online. Association for Computational Linguistics.
  27. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems, volume 35, pages 27730–27744. Curran Associates, Inc.
  28. Understanding factuality in abstractive summarization with FRANK: A benchmark for factuality metrics. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4812–4829, Online. Association for Computational Linguistics.
  29. Check your facts and try again: Improving large language models with external knowledge and automated feedback. arXiv preprint arXiv:2302.12813.
  30. Active learning for natural language generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9862–9877, Singapore. Association for Computational Linguistics.
  31. Subsequence based deep active learning for named entity recognition. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4310–4321, Online. Association for Computational Linguistics.
  32. FactGraph: Evaluating factuality in summarization with semantic graph representations. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3238–3253, Seattle, United States. Association for Computational Linguistics.
  33. Factually consistent summarization via reinforcement learning with textual entailment feedback. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6252–6272, Toronto, Canada. Association for Computational Linguistics.
  34. A neural attention model for abstractive sentence summarization. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 379–389, Lisbon, Portugal. Association for Computational Linguistics.
  35. Active learning for sequence tagging with deep pre-trained models and Bayesian uncertainty estimates. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1698–1712, Online. Association for Computational Linguistics.
  36. Deep active learning for named entity recognition. In International Conference on Learning Representations.
  37. Trusting your evidence: Hallucinate less with context-aware decoding. arXiv preprint arXiv:2305.14739.
  38. Retrieval augmentation reduces hallucination in conversation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3784–3803, Punta Cana, Dominican Republic. Association for Computational Linguistics.
  39. Contrastive learning reduces hallucination in conversations. Proceedings of the AAAI Conference on Artificial Intelligence, 37(11):13618–13626.
  40. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  41. Active learning for abstractive text summarization. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5128–5152, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  42. A stitch in time saves nine: Detecting and mitigating hallucinations of llms by validating low-confidence generation. arXiv preprint arXiv:2307.03987.
  43. David Wan and Mohit Bansal. 2022. FactPEGASUS: Factuality-aware pre-training and fine-tuning for abstractive summarization. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1010–1028, Seattle, United States. Association for Computational Linguistics.
  44. Faithfulness-aware decoding strategies for abstractive summarization. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2864–2880, Dubrovnik, Croatia. Association for Computational Linguistics.
  45. Asking and answering questions to evaluate the factual consistency of summaries. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5008–5020, Online. Association for Computational Linguistics.
  46. Context-aware information-theoretic causal de-biasing for interactive sequence labeling. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3436–3448, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  47. Fine-grained human feedback gives better rewards for language model training. Advances in Neural Information Processing Systems, 36.
  48. Which llm to play? convergence-aware online model selection with time-increasing bandits. arXiv preprint arXiv:2403.07213.
  49. Harnessing the power of llms in practice: A survey on chatgpt and beyond. ACM Transactions on Knowledge Discovery from Data.
  50. AcTune: Uncertainty-based active self-training for active fine-tuning of pretrained language models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1422–1436, Seattle, United States. Association for Computational Linguistics.
  51. AlignScore: Evaluating factual consistency with a unified alignment function. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11328–11348, Toronto, Canada. Association for Computational Linguistics.
  52. Bertscore: Evaluating text generation with bert. In International Conference on Learning Representations.
  53. Benchmarking Large Language Models for News Summarization. Transactions of the Association for Computational Linguistics, 12:39–57.
  54. A survey of active learning for natural language processing. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6166–6190, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  55. A survey of large language models. arXiv:2303.18223.
  56. Towards a unified multi-dimensional evaluator for text generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2023–2038, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (8)
  1. Yu Xia (65 papers)
  2. Xu Liu (213 papers)
  3. Tong Yu (119 papers)
  4. Sungchul Kim (65 papers)
  5. Ryan A. Rossi (124 papers)
  6. Anup Rao (47 papers)
  7. Tung Mai (32 papers)
  8. Shuai Li (295 papers)
Citations (2)
View on Semantic Scholar