From the 1 of 16 linked papers with an AI index.
6 papers · 1 filter
LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models
Shuang Liang, Haoyang Zhou, Yifan Gong +2
The paper introduces LEEPS, a latent-guided explore‑exploit prompt sampler that selects prompts before rollout to reduce wasted generation budget and improve reinforcement learning…
Stop When Further Reasoning Won't Help: Attention-State Adaptive Generation in Reasoning Models
Jiakai Li, Ke Qin, Rongzheng Wang +4
By incorporating test-time compute scaling, large reasoning models (LRMs) can solve complex problems through explicit chain-of-thought (CoT) reasoning processes. However, they ofte…
TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM
Haoyang Zhou, Li Kong, Shijie Ren +4
Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing token…
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty
Chao Xue, Yao Wang, Mengqiao Liu +11
Recent advancements in the Generative Reward Model (GRM) have demonstrated its potential to enhance the reasoning abilities of LLMs through Chain-of-Thought (CoT) prompting. Despit…
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
Chao Xue, Yao Wang, Mengqiao Liu +11
Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after conve…
DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering
Jiakai Li, Rongzheng Wang, Yizhuo Ma +3
While large language models (LLMs) show considerable promise across various fields, they have notable limitations in handling multi-document question answering (Multi-doc QA) tasks…