15 papers · 1 filter
Data Selection for Multi-turn Dialogue Instruction Tuning
Bo Li, Shikun Zhang, Wei Ye
Instruction-tuned language models increasingly rely on large multi-turn dialogue corpora, but these datasets are often noisy and structurally inconsistent, with topic drift, repeti…
SteerRM: Debiasing Reward Models via Sparse Autoencoders
Mengyuan Sun, Zhuohao Yu, Weizheng Gu +2
Reward models (RMs) are critical components of alignment pipelines, yet they exhibit biases toward superficial stylistic cues, preferring better-presented responses over semantical…
Adaptive Test-Time Compute Allocation for Block Diffusion Language Models in Complex Reasoning
Yi Lu, Deyang Kong, Jianing Wang +8
Recent advances in block diffusion language models have demonstrated competitive performance and strong scalability on reasoning tasks. However, their test-time compute allocation…
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
Yutao Mou, Zhangchi Xue, Lijun Li +4
While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation be…
SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
Zhuohao Yu, Xingru Jiang, Weizheng Gu +4
Watermarking LLM-generated text is critical for content attribution and misinformation prevention. However, existing methods compromise text quality, require white-box model access…
Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG
Bo Li, Tian Tian, Zhenghua Xu +3
Dynamic retrieval-augmented generation (RAG) allows large language models (LLMs) to fetch external knowledge on demand, offering greater adaptability than static RAG. A central cha…