Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 171 tok/s
Gemini 2.5 Pro 47 tok/s Pro
GPT-5 Medium 32 tok/s Pro
GPT-5 High 36 tok/s Pro
GPT-4o 60 tok/s Pro
Kimi K2 191 tok/s Pro
GPT OSS 120B 445 tok/s Pro
Claude Sonnet 4.5 36 tok/s Pro
2000 character limit reached

Reducing LLM Hallucinations using Epistemic Neural Networks (2312.15576v1)

Published 25 Dec 2023 in cs.CL

Abstract: Reducing and detecting hallucinations in LLMs is an open research problem. In this project, we attempt to leverage recent advances in the field of uncertainty estimation to reduce hallucinations in frozen LLMs. Epistemic neural networks have recently been proposed to improve output joint distributions for large pre-trained models. ENNs are small networks attached to large, frozen models to improve the model's joint distributions and uncertainty estimates. In this work, we train an epistemic neural network on top of the Llama-2 7B model combined with a contrastive decoding feature enhancement technique. We are the first to train an ENN for the next token prediction task and explore the efficacy of this method in reducing hallucinations on the TruthfulQA dataset. In essence, we provide a method that leverages a pre-trained model's latent embeddings to reduce hallucinations.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (19)
  1. Edm3: Event detection as multi-task text generation. ArXiv, abs/2305.16357, 2023. URL https://api.semanticscholar.org/CorpusID:258947208.
  2. Chuang et al. Dola: Decoding by contrasting layers improves factuality in large language models. In Submitted to The Twelfth International Conference on Learning Representations, 2023. URL https://openreview.net/forum?id=Th6NyL07na. under review.
  3. Context-ner : Contextual phrase generation at scale. 2021. URL https://api.semanticscholar.org/CorpusID:265039305.
  4. Instruction tuned models are quick learners. ArXiv, abs/2306.05539, 2023a. URL https://api.semanticscholar.org/CorpusID:259129868.
  5. Targen: Targeted data generation with large language models. ArXiv, abs/2310.17876, 2023b. URL https://api.semanticscholar.org/CorpusID:264555527.
  6. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33:9459–9474, 2020.
  7. Contrastive decoding: Open-ended text generation as optimization, 2023.
  8. Visual instruction tuning, 2023.
  9. OpenAI. Gpt-4 technical report, 2023.
  10. Epistemic neural networks. arXiv preprint arXiv:2107.08924, 2021.
  11. Fine-tuning language models via epistemic neural networks. arXiv preprint arXiv:2211.01568, 2022a.
  12. The neural testbed: Evaluating joint predictions. Advances in Neural Information Processing Systems, 35:12554–12565, 2022b.
  13. Exploring the limits of transfer learning with a unified text-to-text transformer, 2023.
  14. Instructabsa: Instruction learning for aspect based sentiment analysis. ArXiv, abs/2302.08624, 2023. URL https://api.semanticscholar.org/CorpusID:257020097.
  15. BERT rediscovers the classical NLP pipeline. In Anna Korhonen, David Traum, and Lluís Màrquez (eds.), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp.  4593–4601, Florence, Italy, July 2019. Association for Computational Linguistics. doi: 10.18653/v1/P19-1452. URL https://aclanthology.org/P19-1452.
  16. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023.
  17. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171, 2022.
  18. Chain-of-thought prompting elicits reasoning in large language models. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (eds.), Advances in Neural Information Processing Systems, volume 35, pp.  24824–24837. Curran Associates, Inc., 2022. URL https://proceedings.neurips.cc/paper_files/paper/2022/file/9d5609613524ecf4f15af0f7b31abca4-Paper-Conference.pdf.
  19. Can llms express their uncertainty? an empirical evaluation of confidence elicitation in llms. arXiv preprint arXiv:2306.13063, 2023.
Citations (6)

Summary

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

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

Open Problems

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

Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

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

List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

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