Skip to content
@CHATS-lab

CHATS-lab

Conversation, Human-AI Technology, and Safety Lab

Pinned Loading

  1. verbalized-sampling verbalized-sampling Public

    Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. …

    Python 813 84

  2. persuasive_jailbreaker persuasive_jailbreaker Public

    Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!

    HTML 367 26

Repositories

Showing 10 of 13 repositories
  • VibeLens Public

    Your agent is powerful but it doesn't know you. VibeLens visualizes agent sessions, personalizes your agents, provides dashboard analytics and productivity tips from your real interaction. Supports Claude Code, Codex, Gemini CLI, OpenClaw, and more.

    CHATS-lab/VibeLens's past year of commit activity
    Python 21 MIT 1 0 0 Updated Oct 2, 2026
  • scope_usim Public
    CHATS-lab/scope_usim's past year of commit activity
    Python 4 Apache-2.0 0 1 0 Updated Sep 28, 2026
  • Token-Regularized-Fine-Tuning Public

    Code base for paper: "The Piggyback Hypothesis of Generalization: explaining and mitigating emergent misalignment"

    CHATS-lab/Token-Regularized-Fine-Tuning's past year of commit activity
    Python 3 0 0 0 Updated Sep 22, 2026
  • ppi-eval Public
    CHATS-lab/ppi-eval's past year of commit activity
    Python 0 0 0 0 Updated Aug 27, 2026
  • ToolShield Public

    [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents"

    CHATS-lab/ToolShield's past year of commit activity
    Python 38 MIT 3 1 0 Updated Jul 31, 2026
  • Awesome-Human-AI-Coevolution-Paper-List Public

    An Awesome Human-AI-Coevolution Paperlist Created by CHATS LAB

    CHATS-lab/Awesome-Human-AI-Coevolution-Paper-List's past year of commit activity
    TypeScript 2 0 0 0 Updated Jul 19, 2026
  • LLMs_Encode_Harmfulness_Refusal_Separately Public
    CHATS-lab/LLMs_Encode_Harmfulness_Refusal_Separately's past year of commit activity
    Python 45 7 1 0 Updated Jul 3, 2026
  • shepherd Public

    SHEPHERD: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace

    CHATS-lab/shepherd's past year of commit activity
    HTML 1 0 0 0 Updated Jun 29, 2026
  • coding-agent-safety-monitor Public

    Repository of safety monitor for Claude Code

    CHATS-lab/coding-agent-safety-monitor's past year of commit activity
    Python 7 MIT 1 0 0 Updated May 13, 2026
  • LLMimic Public

    An gamified, interactive, and role-play-based AI literacy tutorial that mitigates the effects of AI persuasion.

    CHATS-lab/LLMimic's past year of commit activity
    Python 0 MIT 1 0 0 Updated Apr 19, 2026
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…