University of California, Santa Cruz - NLP Team

university

https://github.com/nlp-ucsc

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

parsa-mz authored a paper about 2 months ago

Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency

parsa-mz authored a paper about 2 months ago

Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form

parsa-mz authored a paper about 2 months ago

REPOT: Recoverable Program-of-Thought via Checkpoint Repair

View all activity

authored 4 papers about 2 months ago

Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency

Paper • 2608.16003 • Published Aug 17 • 4

Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form

Paper • 2608.15022 • Published Aug 15 • 4

REPOT: Recoverable Program-of-Thought via Checkpoint Repair

Paper • 2605.30052 • Published May 28 • 6

Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models

Paper • 2312.14346 • Published Dec 22, 2023 • 1

submitted 2 papers to Daily Papers about 2 months ago

Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency

Paper • 2608.16003 • Published Aug 17 • 4

Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form

Paper • 2608.15022 • Published Aug 15 • 4

submitted a paper to Daily Papers 4 months ago

REPOT: Recoverable Program-of-Thought via Checkpoint Repair

Paper • 2605.30052 • Published May 28 • 6

authored a paper 4 months ago

AgentAtlas: Beyond Outcome Leaderboards for LLM Agents

Paper • 2605.20530 • Published May 19