Papers with token-level MDP perspective of
Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, including instruction following, mathematical problem solving, and coding generation. |
| Approach: | They propose a method that truncates both preferred and dispreferred responses to match the shorter one’s length. |
| Outcome: | The proposed approach improves over standard implementations and achieves 11.8 points in AlpacaEval 2 and overall improvements across downstream tasks. |