Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Where Do LLM Ensemble Gains Come From? Decomposing Candidate Value, Diversity, and Aggregation
Donghwan Kim
LLM ensemble gains are often measured against a single baseline, but the value attributed to additional candidates can change with the comparison used. We study an LLM aggregator u…
cs.CL2026
Are Diversity Metrics Measuring Diversity? A Capability-Controlled Audit of Majority-Vote Gain in LLM Ensembles
Donghwan Kim
Majority voting over LLMs is widely assumed to benefit from diversity, and diversity measures are used to choose which models to combine. We ask whether five such measures track di…
cs.CL2026
LLM-as-a-Judge Scores Are Unreliable Optimization Signals in Closed-Loop Table Recognition
Donghwan Kim
LLM-as-a-judge is widely used to provide feedback and selection signals in closedloop regeneration, but this use remains insufficiently validated. We study it in table recognition,…