METR / eval-analysis-publicLinks
Public repository containing METR's DVC pipeline for eval data analysis
β117Updated 6 months ago
Alternatives and similar repositories for eval-analysis-public
Users that are interested in eval-analysis-public are comparing it to the libraries listed below
Sorting:
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" π€β75Updated 10 months ago
- accompanying material for sleep-time compute paperβ115Updated 5 months ago
- A DSPy-based implementation of the tree of thoughts method (Yao et al., 2023) for generating persuasive argumentsβ89Updated last week
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)β91Updated 8 months ago
- Train your own SOTA deductive reasoning modelβ107Updated 7 months ago
- β57Updated 8 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.β53Updated 5 months ago
- Source code for the collaborative reasoner research project at Meta FAIR.β102Updated 5 months ago
- β68Updated 4 months ago
- β232Updated 3 months ago
- Experimental Code for StructuredRAG: JSON Response Formatting with Large Language Modelsβ111Updated 6 months ago
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.β98Updated 2 months ago
- Prompts used in the Automated Auditing Blog Postβ103Updated 2 months ago
- π§ Compare how Agent systems perform on several benchmarks. ππβ102Updated 2 months ago
- Code for "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs"β55Updated 7 months ago
- ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems. (EMNLP 2024 Demo)β87Updated 3 weeks ago
- Just a bunch of benchmark logs for different LLMsβ119Updated last year
- β97Updated 2 months ago
- An attribution library for LLMsβ42Updated last year
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generaβ¦β96Updated this week
- β70Updated last week
- A library for benchmarking the Long Term Memory and Continual learning capabilities of LLM based agents. With all the tests and code youβ¦β79Updated 9 months ago
- A framework for pitting LLMs against each other in an evolving library of games ββ33Updated 5 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.β184Updated 7 months ago
- β136Updated this week
- β40Updated 9 months ago
- Automatic Prompt Optimizationβ45Updated last year
- A framework for optimizing DSPy programs with RLβ191Updated this week
- Doing simple retrieval from LLM models at various context lengths to measure accuracyβ104Updated 2 weeks ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.β24Updated 3 weeks ago