Papers
Topics
Authors
Recent
Search
2000 character limit reached

Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study

Published 12 Jan 2024 in cs.SE, cs.CL, and cs.LG | (2402.05939v1)

Abstract: LLMs have been widely employed in programming language analysis to enhance human productivity. Yet, their reliability can be compromised by various code distribution shifts, leading to inconsistent outputs. While probabilistic methods are known to mitigate such impact through uncertainty calibration and estimation, their efficacy in the language domain remains underexplored compared to their application in image-based tasks. In this work, we first introduce a large-scale benchmark dataset, incorporating three realistic patterns of code distribution shifts at varying intensities. Then we thoroughly investigate state-of-the-art probabilistic methods applied to CodeLlama using these shifted code snippets. We observe that these methods generally improve the uncertainty awareness of CodeLlama, with increased calibration quality and higher uncertainty estimation~(UE) precision. However, our study further reveals varied performance dynamics across different criteria (e.g., calibration error vs misclassification detection) and trade-off between efficacy and efficiency, highlighting necessary methodological selection tailored to specific contexts.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. code2seq: Generating sequences from structured representations of code. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net.
  2. code2vec: learning distributed representations of code. Proc. ACM Program. Lang., 3(POPL):40:1–40:29.
  3. Weight uncertainty in neural network. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015, volume 37 of JMLR Workshop and Conference Proceedings, pages 1613–1622. JMLR.org.
  4. Glenn W Brier. 1950. Verification of forecasts expressed in terms of probability. Monthly weather review, 78(1):1–3.
  5. PYEVOLVE: automating frequent code changes in python ML systems. In 45th IEEE/ACM International Conference on Software Engineering, ICSE 2023, Melbourne, Australia, May 14-20, 2023, pages 995–1007. IEEE.
  6. Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016, volume 48 of JMLR Workshop and Conference Proceedings, pages 1050–1059. JMLR.org.
  7. Deep Bayesian active learning with image data. In Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 1183–1192. PMLR.
  8. On calibration of modern neural networks. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017, volume 70 of Proceedings of Machine Learning Research, pages 1321–1330. PMLR.
  9. Dan Hendrycks and Kevin Gimpel. 2017. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net.
  10. Bayesian active learning for classification and preference learning. CoRR, abs/1112.5745.
  11. Codes: Towards code model generalization under distribution shift. In 45th IEEE/ACM International Conference on Software Engineering: New Ideas and Emerging Results, NIER@ICSE, Melbourne, Australia, May 14-20, 2023, pages 1–6. IEEE.
  12. Contrastive code representation learning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5954–5971, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  13. Code prediction by feeding trees to transformers. In 43rd IEEE/ACM International Conference on Software Engineering, ICSE 2021, Madrid, Spain, 22-30 May 2021, pages 150–162. IEEE.
  14. Variational dropout and the local reparameterization trick. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, pages 2575–2583.
  15. Large language models are zero-shot reasoners. In NeurIPS.
  16. Simple and scalable predictive uncertainty estimation using deep ensembles. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pages 6402–6413.
  17. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, pages 7167–7177.
  18. Uncertainty-aware bootstrap learning for joint extraction on distantly-supervised data. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1349–1358, Toronto, Canada. Association for Computational Linguistics.
  19. Enhancing the reliability of out-of-distribution image detection in neural networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net.
  20. Simple and principled uncertainty estimation with deterministic deep learning via distance awareness. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
  21. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net.
  22. Codexglue: A machine learning benchmark dataset for code understanding and generation. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual.
  23. David JC MacKay. 1992. Bayesian interpolation. Neural computation, 4(3):415–447.
  24. A simple baseline for bayesian uncertainty in deep learning. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pages 13132–13143.
  25. George A Miller. 1995. Wordnet: a lexical database for english. Communications of the ACM, 38(11):39–41.
  26. Obtaining well calibrated probabilities using bayesian binning. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, January 25-30, 2015, Austin, Texas, USA, pages 2901–2907. AAAI Press.
  27. Impact of evaluation methodologies on code summarization. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4936–4960, Dublin, Ireland. Association for Computational Linguistics.
  28. Uncertainty quantification in scientific machine learning: Methods, metrics, and comparisons. J. Comput. Phys., 477:111902.
  29. On the generalizability of neural program models with respect to semantic-preserving program transformations. Information and Software Technology, 135:106552.
  30. Out-of-distribution detection and selective generation for conditional language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net.
  31. Code llama: Open foundation models for code. CoRR, abs/2308.12950.
  32. Lewis Smith and Yarin Gal. 2018. Understanding measures of uncertainty for adversarial example detection. In Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, UAI 2018, Monterey, California, USA, August 6-10, 2018, pages 560–569. AUAI Press.
  33. Can you trust your model’s uncertainty? evaluating predictive uncertainty under dataset shift. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pages 13969–13980.
  34. Plex: Towards reliability using pretrained large model extensions. CoRR, abs/2207.07411.
  35. Uncertainty estimation using a single deep deterministic neural network. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, volume 119 of Proceedings of Machine Learning Research, pages 9690–9700. PMLR.
  36. Uncertainty estimation of transformer predictions for misclassification detection. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8237–8252, Dublin, Ireland. Association for Computational Linguistics.
  37. Hongjun Wang and Yisen Wang. 2022. Self-ensemble adversarial training for improved robustness. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net.
  38. Dissector: input validation for deep learning applications by crossing-layer dissection. In ICSE ’20: 42nd International Conference on Software Engineering, Seoul, South Korea, 27 June - 19 July, 2020, pages 727–738. ACM.
  39. Adversarial sample detection for deep neural network through model mutation testing. In Proceedings of the 41st International Conference on Software Engineering, ICSE 2019, Montreal, QC, Canada, May 25-31, 2019, pages 1245–1256. IEEE / ACM.
  40. Sequence level contrastive learning for text summarization. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022, pages 11556–11565. AAAI Press.
  41. On uncertainty calibration and selective generation in probabilistic neural summarization: A benchmark study. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2980–2992, Singapore. Association for Computational Linguistics.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

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

Continue Learning

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

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

Collections

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

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