Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 33

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

Chuang, Yung-Sung, Qiu, Linlu, Hsieh, Cheng-Yu, Krishna, Ranjay, Kim, Yoon, Glass, James R.·2024·Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2024.emnlp-main.84

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 An illustration of the Lookback Lens . We extract attention weights and calculate the lookback ratios for all layers and all heads. We train a linear classifier on the concatenated features to predict truthfulness of the generation.
Figure 1 An illustration of the Lookback Lens . We extract attention weights and calculate the lookback ratios for all layers and all heads. We train a linear classifier on the concatenated features to predict truthfulness of the generation.CC-BY · From the PDF
Figure 2 Lookback Lens Guided Decoding : sample multiple chunk candidates, compute lookback ratios from attention maps to be scored by Lookback Lens , and select the best candidate that is less likely to be hallucinations.
Figure 2 Lookback Lens Guided Decoding : sample multiple chunk candidates, compute lookback ratios from attention maps to be scored by Lookback Lens , and select the best candidate that is less likely to be hallucinations.CC-BY · From the PDF
Figure 3 Qualitative example on XSum using the LLaMA-2-7B-Chat model with greedy decoding and Lookback Lens Guided Decoding . The numbers in the parenthesis show the predicted scores from the Lookback Lens .
Figure 3 Qualitative example on XSum using the LLaMA-2-7B-Chat model with greedy decoding and Lookback Lens Guided Decoding . The numbers in the parenthesis show the predicted scores from the Lookback Lens .CC-BY · From the PDF
Figure 4 Screenshot of human annotation interface.
Figure 4 Screenshot of human annotation interface.CC-BY · From the PDF
Figure 5 Top-10 positive/negative heads ranked from top to the bottom by the magnitude of their coefficients in the Lookback Lens classifier.
Figure 5 Top-10 positive/negative heads ranked from top to the bottom by the magnitude of their coefficients in the Lookback Lens classifier.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 1 references

Research works printed but not linked: 43

  1. Amos Azaria and Tom Mitchell. 2023. The internal state of an llm knows when it's lying. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 967-976.
  2. Dzmitry Bahdanau, Kyung Hyun Cho, and Yoshua Ben- gio. 2015. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations, ICLR 2015.
  3. Collin Burns, Haotian Ye, Dan Klein, and Jacob Stein- hardt. 2023. Discovering latent knowledge in lan- guage models without supervision. In The Eleventh International Conference on Learning Representa- tions.
  4. James Campbell, Richard Ren, and Phillip Guo. 2023. Localizing lying in llama: Understanding in- structed dishonesty on true-false questions through prompting, probing, and patching. arXiv preprint arXiv:2311.15131. · arXiv
  5. Jifan Chen, Grace Kim, Aniruddh Sriram, Greg Durrett, and Eunsol Choi. 2023. Complex claim verification with evidence retrieved in the wild. arXiv preprint arXiv:2305.11859. · arXiv
  6. Shiqi Chen, Miao Xiong, Junteng Liu, Zhengxuan Wu, Teng Xiao, Siyang Gao, and Junxian He. 2024a. In-context sharpness as alerts: An inner represen- tation perspective for hallucination mitigation. arXiv preprint arXiv:2403.01548. · arXiv
  7. Zhongzhi Chen, Xingwu Sun, Xianfeng Jiao, Fengzong Lian, Zhanhui Kang, Di Wang, and Chengzhong Xu. 2024b. Truth forest: Toward multi-scale truthful- ness in large language models through intervention without tuning. In Proceedings of the AAAI Con- ference on Artificial Intelligence, volume 38, pages 20967-20974.
  8. I Chern, Steffi Chern, Shiqi Chen, Weizhe Yuan, Kehua Feng, Chunting Zhou, Junxian He, Graham Neubig, Pengfei Liu, et al. 2023. Factool: Factuality detec- tion in generative ai-a tool augmented framework for multi-task and multi-domain scenarios. arXiv preprint arXiv:2307.13528. · arXiv
  9. Cheng-Han Chiang and Hung-Yi Lee. 2023. Can large language models be an alternative to human evalua- tions? In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers), pages 15607-15631.
  10. Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James R Glass, and Pengcheng He. 2024. Dola: Decoding by contrasting layers improves factuality in large language models. In The Twelfth International Conference on Learning Representations.
  11. Kevin Clark, Urvashi Khandelwal, Omer Levy, and Christopher D Manning. 2019. What does bert look at? an analysis of bert's attention. arXiv preprint arXiv:1906.04341. · arXiv
  12. Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2019. Plug and play language models: A simple approach to controlled text generation. In International Conference on Learning Representa- tions.
  13. Alexander R Fabbri, Chien-Sheng Wu, Wenhao Liu, and Caiming Xiong. 2021. Qafacteval: Improved qa-based factual consistency evaluation for summa- rization. arXiv preprint arXiv:2112.08542. · arXiv
  14. Yaru Hao, Li Dong, Furu Wei, and Ke Xu. 2021. Self- attention attribution: Interpreting information interac- tions inside transformer. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 12963-12971.
  15. Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2021. Debertav3: Improving deberta using electra-style pre- training with gradient-disentangled embedding shar- ing. Preprint, arXiv:2111.09543. · arXiv
  16. Or Honovich, Roee Aharoni, Jonathan Herzig, Hagai Taitelbaum, Doron Kukliansy, Vered Cohen, Thomas Scialom, Idan Szpektor, Avinatan Hassidim, and Yossi Matias. 2022. True: Re-evaluating factual consistency evaluation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3905-3920.
  17. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of halluci- nation in natural language generation. ACM Comput- ing Surveys, 55(12):1-38.
  18. Nikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace, and Colin Raffel. 2023. Large language models struggle to learn long-tail knowledge. In In- ternational Conference on Machine Learning, pages 15696-15707.
  19. PMLR.
  20. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Red- field, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Ken- ton Lee, et al. 2019. Natural questions: a benchmark for question answering research. Transactions of the Association for Computational Linguistics, 7:453- 466.
  21. Philippe Laban, Tobias Schnabel, Paul N Bennett, and Marti A Hearst. 2022. Summac: Re-visiting nli- based models for inconsistency detection in summa- rization. Transactions of the Association for Compu- tational Linguistics, 10:163-177.
  22. Junyi Li, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, and Ji-Rong Wen. 2023. Halueval: A large- scale hallucination evaluation benchmark for large language models. In Proceedings of the 2023 Con- ference on Empirical Methods in Natural Language Processing, pages 6449-6464.
  23. Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. 2024. Inference- time intervention: Eliciting truthful answers from a language model. Advances in Neural Information Processing Systems, 36.
  24. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74-81.
  25. Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paran- jape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. Lost in the middle: How language mod- els use long contexts. Transactions of the Association for Computational Linguistics, 12:157-173.
  26. Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, and Chenguang Zhu. 2023. G-eval: Nlg evaluation using gpt-4 with better human align- ment. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2511-2522.
  27. Minh-Thang Luong, Hieu Pham, and Christopher D Manning. 2015. Effective approaches to attention- based neural machine translation. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1412-1421.
  28. Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. When not to trust language models: Investigating effectiveness of parametric and non-parametric mem- ories. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers), pages 9802-9822.
  29. Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Wei Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. Factscore: Fine-grained atomic evaluation of factual precision in long form text generation. arXiv preprint arXiv:2305.14251. · arXiv
  30. Shashi Narayan, Shay B Cohen, and Mirella Lapata. 2018. Don't give me the details, just the summary! topic-aware convolutional neural networks for ex- treme summarization. In Proceedings of the 2018 Conference on Empirical Methods in Natural Lan- guage Processing, pages 1797-1807.
  31. Ella Neeman, Roee Aharoni, Or Honovich, Leshem Choshen, Idan Szpektor, and Omri Abend. 2023. Disentqa: Disentangling parametric and contextual knowledge with counterfactual question answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10056-10070.
  32. Tal Schuster, Adam Fisch, and Regina Barzilay. 2021. Get your vitamin C! robust fact verification with contrastive evidence. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 624-643, Online. As- sociation for Computational Linguistics. · DOI · Paper page
  33. Abigail See, Peter J Liu, and Christopher D Manning. 2017. Get to the point: Summarization with pointer- generator networks. In Proceedings of the 55th An- nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1073- 1083.
  34. Weijia Shi, Xiaochuang Han, Mike Lewis, Yulia Tsvetkov, Luke Zettlemoyer, and Scott Wen-tau Yih. 2023. Trusting your evidence: Hallucinate less with context-aware decoding. arXiv preprint arXiv:2305.14739. · arXiv
  35. Adi Simhi, Jonathan Herzig, Idan Szpektor, and Yonatan Belinkov. 2024. Constructing benchmarks and inter- ventions for combating hallucinations in llms. arXiv preprint arXiv:2404.09971. · arXiv
  36. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. In NAACL-HLT.
  37. Hugo Touvron, Louis Martin, Kevin Stone, Peter Al- bert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open founda- tion and fine-tuned chat models. arXiv preprint arXiv:2307.09288. · arXiv
  38. Shikhar Vashishth, Shyam Upadhyay, Gaurav Singh Tomar, and Manaal Faruqui. 2019. Attention in- terpretability across nlp tasks. arXiv preprint arXiv:1909.11218. · arXiv
  39. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30.
  40. Kevin Yang and Dan Klein. 2021. Fudge: Controlled text generation with future discriminators. In Pro- ceedings of the 2021 Conference of the North Amer- ican Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3511-3535.
  41. Shaolei Zhang, Tian Yu, and Yang Feng. 2024. Truthx: Alleviating hallucinations by editing large language models in truthful space. arXiv preprint arXiv:2402.17811. · arXiv
  42. Yuan Zhang, Jason Baldridge, and Luheng He. 2019b. PAWS: Paraphrase Adversaries from Word Scram- bling. In Proc. of NAACL.
  43. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. 2024. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems, 36.

Cited by

See all 33

Metadata

Authors
Chuang, Y.-S., Qiu, L., Hsieh, C.-Y., Krishna, R., Kim, Y., & Glass, J. R.
Venue
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Published
2024
Pages
1419-1436
Cited by
33
References
1

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps. https://app.cochat.ai/papers/10.18653/v1/2024.emnlp-main.84
The paper
Chuang, Y.-S., Qiu, L., Hsieh, C.-Y., Krishna, R., Kim, Y., & Glass, J. R. (2024). Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2024.emnlp-main.84

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.