Search papers, labs, and topics across Lattice.
Affiliation:
5
0
5
A fixed span can recover most of the benefits of movable low-rank factors in LLM adaptation, achieving superior performance with drastically fewer trainable parameters.
Context-sensitive hallucinations in LLMs can be mitigated by a new optimization technique that rewards step-level consistency, leading to significant improvements in reasoning accuracy.
Dense retrievers miss the mark on answerability, dropping QA performance drastically despite high semantic relevance, revealing a critical oversight in RAG systems.
OPSD can backfire, leading to rote memorization instead of enhancing reasoning, but a novel decomposition approach reveals a path to meaningful improvements.
Ignoring individual olfactory profiles can degrade odor prediction accuracy, but structured integration leads to significant improvements in scent matching for audiovisual content.
