Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs
Zihan Chen, Yiming Zhang, Wenxiang Geng +2
Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high performance on in-distribution benc…
cs.LG2025
Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?
Zihan Chen, Yiming Zhang, Hengguang Zhou +3
Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).Despite recent benchmark gains reported for RL, we find th…
cs.LG2025
OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
Liang Lin, Zhihao Xu, Junhao Dong +10
Large language model (LLM) alignment faces a critical dilemma when addressing multiple human preferences: improvements in one dimension frequently come at the expense of others, cr…