Search papers, labs, and topics across Lattice.
5
0
5
1
Channel-wise contributions in MBR decoding reveal distinct characteristics that could significantly improve text generation quality when properly weighted.
Low-resource languages are structurally more distinct from English than their high-resource counterparts, revealing critical insights into LLM multilinguality.
Catch AI's academic dishonesty: HalluCiteChecker spots bogus citations in seconds, lightening the load for reviewers drowning in AI-assisted papers.
LLMs' factual knowledge is surprisingly brittle: simply changing an entity's surface form in a question (e.g., using an abbreviation instead of the full name) can drastically alter the answer.
Translation metrics can exhibit significant cross-lingual scoring bias, meaning they unfairly penalize or reward translations depending on the language, even when the quality is the same.
