Search papers, labs, and topics across Lattice.
2
0
4
Up to 31.6% of correct model solutions rely on semantically invalid reasoning traces that look deceptively sound, revealing that chain-of-thought generation frequently acts as an unfaithful facade rather than a true computation graph.
LLMs struggle with instruction following in Indic languages despite progress in high-resource languages, as shown by a new benchmark spanning 14 languages.
