Papers
Topics
Authors
Recent
2000 character limit reached

SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes (2403.07726v3)

Published 12 Mar 2024 in cs.CL

Abstract: This paper presents the results of the SHROOM, a shared task focused on detecting hallucinations: outputs from natural language generation (NLG) systems that are fluent, yet inaccurate. Such cases of overgeneration put in jeopardy many NLG applications, where correctness is often mission-critical. The shared task was conducted with a newly constructed dataset of 4000 model outputs labeled by 5 annotators each, spanning 3 NLP tasks: machine translation, paraphrase generation and definition modeling. The shared task was tackled by a total of 58 different users grouped in 42 teams, out of which 27 elected to write a system description paper; collectively, they submitted over 300 prediction sets on both tracks of the shared task. We observe a number of key trends in how this approach was tackled -- many participants rely on a handful of model, and often rely either on synthetic data for fine-tuning or zero-shot prompting strategies. While a majority of the teams did outperform our proposed baseline system, the performances of top-scoring systems are still consistent with a random handling of the more challenging items.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. SHROOM-INDElab at SemEval-2024 Task 6: Zero- and Few-Shot LLM-Based Classification for Hallucination Detection.
  2. TU Wien at SemEval-2024 Task 6: Unifying Model-Agnostic and Model-Aware Techniques for Hallucination Detection.
  3. Hallucinations and Related Observable Overgeneration Mistakes Detection.
  4. IRIT-Berger-Levrault at SemEval-2024 Task 6: How Sensitive Sentence Embeddings are to Hallucinations?
  5. Maha Bhaashya at SemEval-2024 Task 6: Zero-Shot Multi-task Hallucination Detection.
  6. MALTO at SemEval-2024 Task 6: Leveraging Synthetic Data for LLM Hallucination Detection.
  7. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 632–642, Lisbon, Portugal. Association for Computational Linguistics.
  8. Octavian Brodoceanu. 2024. octavianB at SemEval-2024 Task 6: An exploration of humanlike qualities of hallucinated LLM texts.
  9. Cheolyeon Byun. 2024. Byun at SemEval-2024 Task 6: Text Classification on Hallucinating Text with Simple Data Augmentation.
  10. OPDAI at SemEval-2024 Task 6: Small LLMs can Accelerate Hallucination Detection with Weakly Supervised Data.
  11. AlphaIntellect at SemEval-2024 Task 6: Detection of Hallucinations in Generated Text.
  12. Mathias Creutz. 2018. Open subtitles paraphrase corpus for six languages. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA).
  13. Souvik Das and Rohini Srihari. 2024. Compos Mentis at SemEval-2024 Task 6: A Multi-Faceted Role-based Large Language Model Ensemble to Detect Hallucination.
  14. PROTAUGMENT: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning. 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 2454–2466, Online. Association for Computational Linguistics.
  15. Evaluating attribution in dialogue systems: The BEGIN benchmark. Transactions of the Association for Computational Linguistics, 10:1066–1083.
  16. SLPL SHROOM at SemEval-2024 Task 6: A comprehensive study on models ability to detect hallucination.
  17. Interpretable word sense representations via definition generation: The case of semantic change analysis. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3130–3148, Toronto, Canada. Association for Computational Linguistics.
  18. AILS-NTUA at SemEval-2024 Task 6: Efficient model tuning for hallucination detection and analysis.
  19. Looking for a needle in a haystack: A comprehensive study of hallucinations in neural machine translation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1059–1075, Dubrovnik, Croatia. Association for Computational Linguistics.
  20. A survey on automated fact-checking. Transactions of the Association for Computational Linguistics, 10:178–206.
  21. DUTh at SemEval-2024 Task 6: Comparing Pre-trained Models on Sentence Similarity Evaluation for Detecting of Hallucinations and Related Observable Overgeneration Mistakes.
  22. Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12):1–38.
  23. Mistral 7b. arXiv preprint arXiv:2310.06825.
  24. Pollice Verso at SemEval-2024 Task 6: The Roman Empire Strikes Back.
  25. Philipp Koehn. 2005. Europarl: A parallel corpus for statistical machine translation. In Proceedings of Machine Translation Summit X: Papers, pages 79–86, Phuket, Thailand.
  26. 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.
  27. TruthfulQA: Measuring how models mimic human falsehoods. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3214–3252, Dublin, Ireland. Association for Computational Linguistics.
  28. 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.
  29. HIT-MI&T Lab at SemEval-2024 Task 6: DeBERTa-based Entailment Model is a Reliable Hallucination Detector.
  30. Yu-An Lu. 2024. 0x.Yuan at SemEval-2024 Task 6: Ensemble Multi LLMs to Detect Hallucinations in Text .
  31. DeepPavlov at SemEval-2024 Task 6: Detection of Hallucinations and Overgeneration Mistakes with an Ensemble of Transformer-based Models.
  32. 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.
  33. NU-RU at SemEval-2024 Task 6: Hallucination and Related Observable Overgeneration Mistake Detection Using Hypothesis-Target Similarity and SelfCheckGPT.
  34. 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.
  35. Halu-NLP at SemEval-2024 Task 6: MetaCheckGPT - A Multi-task Hallucination Detection using LLM uncertainty and meta-models.
  36. Semeval-2022 task 1: CODWOE – comparing dictionaries and word embeddings. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1–14, Seattle, United States. Association for Computational Linguistics.
  37. Timothee Mickus and Raúl Vázquez. 2023. Why bother with geometry? on the relevance of linear decompositions of transformer embeddings. In Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 127–141, Singapore. Association for Computational Linguistics.
  38. What can we learn from collective human opinions on natural language inference data? In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9131–9143, Online. Association for Computational Linguistics.
  39. No language left behind: Scaling human-centered machine translation.
  40. Definition modeling: Learning to define word embeddings in natural language. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, USA, pages 3259–3266. AAAI Press.
  41. HaRMoNEE at SemEval-2024 Task 6: Tuning-based Approaches to Hallucination Recognition.
  42. UMUTeam at SemEval-2024 Task 6: Leveraging Zero-Shot Learning for Detecting Hallucinations and Related Observable Overgeneration Mistakes.
  43. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics.
  44. Codalab competitions: An open source platform to organize scientific challenges. Journal of Machine Learning Research, 24(198):1–6.
  45. POTATO: The portable text annotation tool. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 327–337, Abu Dhabi, UAE. Association for Computational Linguistics.
  46. HalluSafe at SemEval-2024 Task 6: An NLI-based Approach to Make LLMs Safer by Better Detecting Hallucinations and Overgeneration Mistakes.
  47. The curious case of hallucinations in neural machine translation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1172–1183, Online. Association for Computational Linguistics.
  48. Object hallucination in image captioning. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4035–4045, Brussels, Belgium. Association for Computational Linguistics.
  49. SmurfCat at SemEval-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection.
  50. Bolaca at SemEval-2024 Task 6.
  51. MARiA at SemEval-2024 Task 6: Hallucination Detection Through LLMs and MNLI and and Cosine similarity.
  52. Vincent Segonne and Timothee Mickus. 2023. Definition modeling : To model definitions. generating definitions with little to no semantics. In Proceedings of the 15th International Conference on Computational Semantics, pages 258–266, Nancy, France. Association for Computational Linguistics.
  53. Marco Siino. 2024. BrainLlama at SemEval-2024 Task 6: Prompting Llama to detect hallucinations and related observable overgeneration mistakes.
  54. Guiding zero-shot paraphrase generation with fine-grained control tokens. In Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023), pages 323–337, Toronto, Canada. Association for Computational Linguistics.
  55. Kees van Deemter. 2024. The Pitfalls of Defining Hallucination. Computational Linguistics, pages 1–10.
  56. Diverse beam search: Decoding diverse solutions from neural sequence models. arXiv preprint arXiv:1610.02424.
  57. Oriol Vinyals and Quoc Le. 2015. A neural conversational model.
  58. Yijun Xiao and William Yang Wang. 2021. On hallucination and predictive uncertainty in conditional language generation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2734–2744, Online. Association for Computational Linguistics.
  59. Pegasus: Pre-training with extracted gap-sentences for abstractive summarization. In International Conference on Machine Learning, pages 11328–11339. PMLR.
  60. Detecting hallucinated content in conditional neural sequence generation. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1393–1404, Online. Association for Computational Linguistics.
  61. Distributed NLI: Learning to predict human opinion distributions for language reasoning. In Findings of the Association for Computational Linguistics: ACL 2022, pages 972–987, Dublin, Ireland. Association for Computational Linguistics.
Citations (15)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Slide Deck Streamline Icon: https://streamlinehq.com

Whiteboard

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up