3 citations · 7 across the 11 of their papers we have counts for
Showing 2026Show 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.LG2026
Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories
Nabira Rashid, Manolis Kellis
We evaluate embedding retrieval where surface form and meaning are pulled apart on purpose: retrieving items that share underlying structure but not wording, in two unrelated domai…