Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

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.

Parsa Mazaheri's profile picture

parsa-mz 
authored 4 papers 3 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
parsa-mz 
submitted 2 papers to Daily Papers 3 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
parsa-mz 
submitted a paper to Daily Papers 6 months ago

REPOT: Recoverable Program-of-Thought via Checkpoint Repair

Paper • 2605.30052 • Published May 28 • 6
parsa-mz 
authored a paper 6 months ago

AgentAtlas: Beyond Outcome Leaderboards for LLM Agents

Paper • 2605.20530 • Published May 19
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs