Submitted by YidaCai 14 LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models Tsinghua NLP Group 1
Submitted by Yinghao Chen 18 StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability? Tsinghua NLP Group 8 2
Submitted by Bingxiang He 29 PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments Tsinghua NLP Group 6 2
Submitted by Chenyang Song 2 DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices Tsinghua NLP Group 2 1
Submitted by Bingxiang He 116 Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe Tsinghua NLP Group 1.03k 6
Submitted by ssz 9 FaithLens: Detecting and Explaining Faithfulness Hallucination Tsinghua NLP Group 105 2