Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Output Discipline Sets the Floor: A Falsification-Guided, Model-Agnostic Agent Protocol for Auditable Hypothesis-Driven Decision Making
Jing Liu, Yongxing Qi, Ping Yao +1
What binds large language models on auditable, hypothesis-driven decision tasks, where every candidate can be checked against the evidence? On the public TCMEval-SDT benchmark for…
cs.AI2026
From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism
Jing Liu, Yongxing Qi, Muchen Jiang +7
Retrieval-Augmented Generation (RAG) grounds LLM generation on retrieved documents, but the standard terminal retrieval stage--dense-vector similarity, optionally followed by reran…