Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
SSA: Improving Performance With a Better Scoring Function
Omar Naim, Swarnadeep Bhar, Jérôme Bolte +1
While transformer models exhibit strong in-context learning (ICL) abilities, they often fail to generalize under simple distribution shifts. We analyze these failures and identify…
cs.CL2026
COCORELI: Enforcing Execution Preconditions for Reliable Collaborative Instruction Following
Swarnadeep Bhar, Omar Naim, Eleni Metheniti +4
Autonomous agents executing human instructions must operate reliably even when instructions are incomplete. While recent approaches improve detection of missing information, detect…
cs.CL2024
Strong hallucinations from negation and how to fix them
Nicholas Asher, Swarnadeep Bhar
Despite great performance on many tasks, language models (LMs) still struggle with reasoning, sometimes providing responses that cannot possibly be true because they stem from logi…