Papers by Yuyan Bu
Beyond Excess and Deficiency: Adaptive Length Bias Mitigation in Reward Models for RLHF (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing efforts to mitigate length bias in reward models have decreased accuracy . achieving an automatic proxy that perfectly replicates human judgment is challenging in practice. |
| Approach: | They propose an adaptive approach that dynamically adjusts the influence of response length in reward evaluations according to the context of the query. |
| Outcome: | The proposed approach reduces unnecessary verbosity while improving overall response quality. |
The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluations of LLMs' moral reasoning capabilities rely on single-step evaluations, ignoring how models adapt to evolving ethical challenges. |
| Approach: | They propose a framework to evaluate evolving moral judgments of large language models (LLMs) using multi-step moral dilemma questionnaires. |
| Outcome: | The proposed framework enables a fine-grained analysis of how LLMs adjust their moral reasoning across escalating dilemmas. |