bradhilton / temporal-clueLinks
Clue inspired puzzles for testing LLM deduction abilities
☆37Updated 2 months ago
Alternatives and similar repositories for temporal-clue
Users that are interested in temporal-clue are comparing it to the libraries listed below
Sorting:
- Train your own SOTA deductive reasoning model☆92Updated 2 months ago
- OpenPipe Reinforcement Learning Experiments☆24Updated 2 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆53Updated 4 months ago
- Lego for GRPO☆28Updated last week
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆139Updated 3 months ago
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 6 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆90Updated 4 months ago
- ☆21Updated 5 months ago
- Simple GRPO scripts and configurations.☆58Updated 3 months ago
- Fine-tunes a student LLM using teacher feedback for improved reasoning and answer quality. Implements GRPO with teacher-provided evaluati…☆43Updated 3 weeks ago
- ☆57Updated last week
- Benchmark that evaluates LLMs using 651 NYT Connections puzzles extended with extra trick words☆93Updated this week
- ☆49Updated 6 months ago
- entropix style sampling + GUI☆26Updated 7 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆60Updated last month
- A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.☆24Updated 2 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆171Updated 4 months ago
- Public Goods Game (PGG) Benchmark: Contribute & Punish is a multi-agent benchmark that tests cooperative and self-interested strategies a…☆36Updated last month
- ☆19Updated 3 weeks ago
- ☆75Updated 2 weeks ago
- ☆36Updated 3 months ago
- ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems. (EMNLP 2024 Demo)☆78Updated 2 months ago
- Accompanying code and SEP dataset for the "Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?" paper.☆52Updated 2 months ago
- ☆33Updated 2 months ago
- Challenges for general-purpose web-browsing AI agents☆58Updated this week
- How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training☆34Updated last month
- Very minimal (and stateless) agent framework☆44Updated 4 months ago
- ☆45Updated last year
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆24Updated last month
- ☆16Updated 4 months ago