CHATS-lab / verbalized-samplingLinks
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. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation.
☆233Updated this week
Alternatives and similar repositories for verbalized-sampling
Users that are interested in verbalized-sampling are comparing it to the libraries listed below
Sorting:
- The State Of The Art, intelligence☆154Updated 2 months ago
- A multi-agent LLM system for detecting and resolving cognitive dissonance.☆268Updated last week
- Routing on Random Forest (RoRF)☆214Updated last year
- An OpenSource Deep Research library with reasoning☆161Updated last month
- Context Engineering Course with DSPy☆195Updated 2 months ago
- ☆104Updated 4 months ago
- ☆152Updated 3 months ago
- ☆79Updated 3 weeks ago
- MCP-based Agent Deep Evaluation System☆136Updated last month
- Salesforce Enterprise Deep Research☆147Updated this week
- DIffbot LLM Inference Server☆201Updated 2 months ago
- The code repository of the paper: Competition and Attraction Improve Model Fusion☆161Updated 2 months ago
- Official repository for "DynaSaur: Large Language Agents Beyond Predefined Actions"☆349Updated 10 months ago
- A Tree Search Library with Flexible API for LLM Inference-Time Scaling☆479Updated last week
- ☆188Updated 10 months ago
- Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)☆446Updated 2 months ago
- ☆84Updated 11 months ago
- Open source RAG evaluation package☆315Updated 2 weeks ago
- ☆110Updated last month
- An alignment auditing agent capable of quickly exploring alignment hypothesis☆609Updated this week
- A user interface for DSPy☆195Updated 3 weeks ago
- 🤖 Headless IDE for AI agents☆200Updated 2 weeks ago
- ☆113Updated 3 months ago
- Real-Time Detection of Hallucinated Entities in Long-Form Generation☆260Updated last week
- Terminal-based AI Coding Agent, similar to Claude Code, OpenAI Codex etc. but works with many more LLMs e.g. Gemini, Groq, Deepseek☆148Updated 5 months ago
- Open-source versioning, tracing, and annotation tooling.☆196Updated last week
- Verifiers for LLM Reinforcement Learning☆77Updated last month
- a Python library that uses Reinforcement Learning (RL) to train LLMs.☆42Updated 2 months ago
- A Text-Based Environment for Interactive Debugging☆272Updated this week
- A toolkit for building computer use AI agents☆176Updated 4 months ago