Search papers, labs, and topics across Lattice.
3
0
7
CoT fine-tuning can slash long-range recall by over 57% in hybrid LLMs, but a simple parameter restoration method can reverse this trend without additional training.
LLMs that ace code generation often fail to grasp intended program semantics, as evidenced by a stark performance decline when generating executable behavioral specifications on the new CodeSpecBench benchmark.
Forget difficulty-based heuristics: InSight leverages weighted mutual information to select RL training data, boosting LLM reasoning and alignment with up to 2.2x speedup.
