6 papers
FlowState: Execution State as Memory for Long-Horizon LLM Agents
Minghao Li, Bangyan Li, Zifan Wang +5
Long-horizon tasks require LLM agents to continually draw on information from earlier interactions. However, retaining the full history increases context costs, while compressing i…
Shared Experience, Separate Learning: Companion Confidence Calibration for LLMs
Shiyu Ni, Keping Bi, Jiafeng Guo +4
Reliable self-assessment is essential for large language models (LLMs), yet they often remain highly confident when their answers are wrong. We study \emph{concurrent confidence ca…
Can LLM Rerankers Predict Their Own Ranking Performance?
Shiyu Ni, Keping Bi, Jiafeng Guo +3
Retrieval effectiveness varies substantially across queries, making it important to estimate ranking quality before relevance judgments are available. Query performance prediction…
Annotation-Efficient Universal Honesty Alignment
Shiyu Ni, Keping Bi, Jiafeng Guo +4
Honesty alignment-the ability of large language models (LLMs) to recognize their knowledge boundaries and express calibrated confidence-is essential for trustworthy deployment. Exi…
Understanding Parametric Knowledge Injection in Retrieval-Augmented Generation
Minghao Tang, Shiyu Ni, Jingtong Wu +2
Context-grounded generation underpins many LLM applications, including long-document question answering (QA), conversational personalization, and retrieval-augmented generation (RA…
PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead
Tao Tan, Yining Qian, Ang Lv +7
Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrad…