Alternatives and similar repositories for emergent-misalignment-persona-features

Users that are interested in emergent-misalignment-persona-features are comparing it to the libraries listed below

• haizelabs / dspy-redteam
  Red-Teaming Language Models with DSPy
  ☆216Updated 7 months ago
• microsoft / llm-steer-instruct
  A method for steering llms to better follow instructions
  ☆53Updated 2 months ago
• invariantlabs-ai / explorer
  A better way of testing, inspecting, and analyzing AI Agent traces.
  ☆40Updated last week
• patronus-ai / Lynx-hallucination-detection
  ☆43Updated last year
• microsoft / EvoPrompt
  Automatic Prompt Optimization
  ☆45Updated last year
• yueqis / API-Based-Agent
  ☆56Updated 3 months ago
• safety-research / open-source-alignment-faking
  Open Source Replication of Anthropic's Alignment Faking Paper
  ☆51Updated 6 months ago
• METR / eval-analysis-public
  Public repository containing METR's DVC pipeline for eval data analysis
  ☆117Updated 6 months ago
• SalesforceAIResearch / CRMArena
  Official Repo for CRMArena and CRMArena-Pro
  ☆118Updated 3 months ago
• ibm-granite / granite-guardian
  The Granite Guardian models are designed to detect risks in prompts and responses.
  ☆118Updated this week
• oriyor / assistantbench
  Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"
  ☆64Updated 10 months ago
• centerforaisafety / emergent-values
  Code for "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs"
  ☆55Updated 7 months ago
• facebookresearch / ZeroSumEval
  A framework for pitting LLMs against each other in an evolving library of games ⚔
  ☆33Updated 5 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆118Updated last year
• Columbia-NLP-Lab / PAPILLON
  Code for our paper PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles
  ☆57Updated 5 months ago
• facebookresearch / matrix
  Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…
  ☆96Updated this week
• JoshuaPurtell / SmallBench
  Small, simple agent task environments for training and evaluation
  ☆18Updated 11 months ago
• pgasawa / BARE
  Leveraging Base Language Models for Few-Shot Synthetic Data Generation
  ☆35Updated 2 months ago
• microsoft / eureka-ml-insights
  A framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings.
  ☆168Updated this week
• facebookresearch / collaborative-reasoner
  Source code for the collaborative reasoner research project at Meta FAIR.
  ☆102Updated 5 months ago
• youdotcom-oss / ydc-deep-research-evals
  you.com's framework for evaluating deep research systems.
  ☆45Updated 4 months ago
• HyperPotatoNeo / RSA
  ☆56Updated last week
• HishamAlyahya / semantic_backprop
  Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" 🤖
  ☆75Updated 10 months ago
• goncalorafaria / qalign
  QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.
  ☆24Updated 3 weeks ago
• princeton-pli / hal-harness
  ☆136Updated this week
• ZeroSumEval / ZeroSumEval
  A framework for pitting LLMs against each other in an evolving library of games ⚔
  ☆34Updated 5 months ago
• stanford-oval / genie-worksheets
  Specification for creating reliable LLM-based conversational agents
  ☆55Updated last week
• VectorInstitute / fed-rag
  A framework for fine-tuning retrieval-augmented generation (RAG) systems.
  ☆130Updated this week
• LLMSELECTOR / LLMSELECTOR
  ☆78Updated last week
• RapidResponseBench / rapidresponsebench
  ☆35Updated 11 months ago