Papers by Peixin Cao
Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for training large language models require additional annotations to adjust to shifted distributions. |
| Approach: | They propose an algorithm that allows LLMs and reward models to update alternatively via a min-max game to improve their alignment. |
| Outcome: | The proposed framework improves existing alignment baselines in terms of LLM helpfulness and harmlessness. |
Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Standard RALMs often neglect their intrinsic knowledge due to the interference from retrieved information. |
| Approach: | They propose a new approach to improve robustness of RALMs by generating sequential reading notes for each retrieved document. |
| Outcome: | The proposed approach outperforms standard RALMs on four open-domain QA benchmarks. |