Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Evidence Integration in Large Language Models
Sebastien Kawada, Manolis Kellis
Despite increasing reliance on LLMs that reason with external evidence supplied by tools, retrieval-augmented generation, other agents, and users, how LLMs integrate such evidence…
cs.CL2026
AsymVerify at SemEval-2026 Task 6: Asymmetric Confidence-Gated Verification for Political Evasion Detection
Sebastien Kawada
Political evasion is difficult to detect because evasive answers often appear cooperative while avoiding concrete commitment. We present AsymVerify, a confidence-gated verification…