Alternatives and similar repositories for open-source-alignment-faking

Users that are interested in open-source-alignment-faking are comparing it to the libraries listed below

• data-for-agents / insta
  Official Repo for InSTA: Towards Internet-Scale Training For Agents
  ☆55Updated 2 months ago
• facebookresearch / matrix
  Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…
  ☆95Updated this week
• allenai / infinigram-api
  ☆81Updated 2 weeks ago
• AlexCuadron / ThinkingAgent
  Systematic evaluation framework that automatically rates overthinking behavior in large language models.
  ☆93Updated 4 months ago
• Alex-Gurung / ReasoningNCP
  Official repo for Learning to Reason for Long-Form Story Generation
  ☆71Updated 5 months ago
• LoryPack / LLM-LieDetector
  Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"
  ☆72Updated last year
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆158Updated 5 months ago
• ContextualAI / CLAIR_and_APO
  Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
  ☆60Updated last year
• ScalingIntelligence / Archon
  Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.
  ☆183Updated 6 months ago
• google-deepmind / latent-multi-hop-reasoning
  [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?
  ☆77Updated 6 months ago
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆172Updated 8 months ago
• arcee-ai / DAM
  ☆54Updated 10 months ago
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆88Updated 11 months ago
• facebookresearch / collaborative-reasoner
  Source code for the collaborative reasoner research project at Meta FAIR.
  ☆103Updated 5 months ago
• RapidResponseBench / rapidresponsebench
  ☆34Updated 10 months ago
• safety-research / SHADE-Arena
  ☆19Updated 3 months ago
• Danau5tin / calculator_agent_rl
  Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.
  ☆52Updated 4 months ago
• sunblaze-ucb / reasoning_ladder
  ☆35Updated 4 months ago
• SalesforceAIResearch / LaTRO
  ☆122Updated 7 months ago
• letta-ai / sleep-time-compute
  accompanying material for sleep-time compute paper
  ☆111Updated 4 months ago
• uq-project / UQ
  UQ: Assessing Language Models on Unsolved Questions
  ☆27Updated 3 weeks ago
• ahstat / episodic-memory-benchmark
  Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…
  ☆53Updated 5 months ago
• pgasawa / BARE
  Leveraging Base Language Models for Few-Shot Synthetic Data Generation
  ☆34Updated last month
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆115Updated last year
• goncalorafaria / qalign
  QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.
  ☆24Updated this week
• benpry / why-think-step-by-step
  Code and data for the paper "Why think step by step? Reasoning emerges from the locality of experience"
  ☆61Updated 5 months ago
• centerforaisafety / emergent-values
  Code for "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs"
  ☆54Updated 6 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆57Updated last month
• katiekang1998 / reasoning_generalization
  ☆33Updated 8 months ago
• sher222 / LeReT
  Learning to Retrieve by Trying - Source code for Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval
  ☆50Updated 10 months ago