6 papers
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
Yinghui He, Ling Yang, Jiarui Liu +6
Long-horizon reasoning in recent LLMs demands that the model switch between distinct skills inside a reasoning chain, such as first doing a math derivation, then using the result t…
Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR
Yongjin Yang, Jiarui Liu, Yinghui He +3
Reinforcement learning with verifiable rewards (RLVR) has been extended from single-domain training to multi-domain reasoning suites spanning mathematics, programming, and science.…
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection
Jiarui Liu, Lechen Zhang, Yongjin Yang +5
Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasoning and general-domain perform…
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
Yinghui He, Simran Kaur, Adithya Bhaskar +7
Current post-training methods in verifiable settings fall into two categories. Reinforcement learning (RLVR) relies on binary rewards, which are broadly applicable and powerful, bu…
Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding
Haneul Yoo, Yongjin Yang, Hwaran Lee
As large language models (LLMs) have advanced rapidly, concerns regarding their safety have become prominent. In this paper, we discover that code-switching in red-teaming queries…
MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty
Yongjin Yang, Haneul Yoo, Hwaran Lee
Despite the massive advancements in large language models (LLMs), they still suffer from producing plausible but incorrect responses. To improve the reliability of LLMs, recent res…