 ZEBRA: Zero-Shot Example-Based Retrieval Augmentation for Commonsense
Question AnsweringConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 Rationale-Aware Answer Verification by Pairwise Self-EvaluationConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 Unpacking DPO and PPO: Disentangling Best Practices for Learning from
Preference Feedback Michal Guerquin Yizhong Wang Hamish Ivison Zeqiu Wu Valentina Pyatkin Nathan Lambert Noah A. Smith Yejin Choi Hannaneh Hajishirzi |
 RaFe: Ranking Feedback Improves Query Rewriting for RAGConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
![SELF-[IN]CORRECT: LLMs Struggle with Refining Self-Generated Responses](https://cdn.parameterlab.de/resized-images/aHR0cHM6Ly9jZG4ucGFyYW1ldGVybGFiLmRlL3BhcGVycy8yNDA0LjA0Mjk4L3BhZ2VzL3BhZ2UtMS1xODBkMzAwLmpwZw?w=256&q=75&f=webp) SELF-[IN]CORRECT: LLMs Struggle with Refining Self-Generated ResponsesAAAI Conference on Artificial Intelligence (AAAI), 2024 |
 Navigate through Enigmatic Labyrinth A Survey of Chain of Thought
Reasoning: Advances, Frontiers and FutureAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
