Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
Transcript-based detection outperforms direct audio processing in identifying spoken hallucinations, revealing a critical gap in current methodologies.
BLADE achieves unprecedented stability in LLM unlearning, outperforming leading methods by up to 9% while remaining robust under extreme scaling and repeated applications.
Conversational structure, not just misinformation framing, is the key to improving spoken claim verification accuracy.
Disinformation detectors trained on Standard American English can suffer catastrophic performance drops (>33% F1) when faced with other English dialects, potentially disadvantaging hundreds of millions of speakers.
