Search papers, labs, and topics across Lattice.
Seoul National University
4
0
5
Even leading MLLMs struggle with object hallucination, revealing critical integration-stage weaknesses that standard benchmarks fail to capture.
Mathematical heuristics, not just reasoning paths, are the key to unlocking LLMs' accuracy in solving math problems.
Conditioning on character arcs boosts RPLA performance by over 40% in novel scenarios, revealing the critical role of psychological evolution in storytelling.
Human psychometric questionnaires mislead our understanding of LLM behavior, revealing a stark contrast between self-reported and actual response patterns.
