ZeroSumEval / ZeroSumEvalLinks
A framework for pitting LLMs against each other in an evolving library of games ⚔
☆35Updated 9 months ago
Alternatives and similar repositories for ZeroSumEval
Users that are interested in ZeroSumEval are comparing it to the libraries listed below
Sorting:
- ☆56Updated last year
- ReBase: Training Task Experts through Retrieval Based Distillation☆29Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆61Updated last year
- Aioli: A unified optimization framework for language model data mixing☆32Updated last year
- ☆91Updated last month
- Official repo for Learning to Reason for Long-Form Story Generation☆74Updated 9 months ago
- Simple GRPO scripts and configurations.☆59Updated 11 months ago
- Small, simple agent task environments for training and evaluation☆19Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆45Updated 4 months ago
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆63Updated 4 months ago
- PyTorch implementation for MRL☆20Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated 3 months ago
- Functional Benchmarks and the Reasoning Gap☆89Updated last year
- Using open source LLMs to build synthetic datasets for direct preference optimization☆72Updated last year
- ☆59Updated last year
- Understanding the correlation between different LLM benchmarks☆29Updated 2 years ago
- EMNLP 2024 "Re-reading improves reasoning in large language models". Simply repeating the question to get bidirectional understanding for…☆28Updated last year
- Verifiers for LLM Reinforcement Learning☆80Updated 9 months ago
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆69Updated last year
- Mixing Language Models with Self-Verification and Meta-Verification☆112Updated last year
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆31Updated 8 months ago
- Codebase accompanying the Summary of a Haystack paper.☆80Updated last year
- ☆53Updated 11 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆26Updated last month
- SCREWS: A Modular Framework for Reasoning with Revisions☆27Updated 2 years ago
- ☆29Updated last month
- ☆41Updated last year
- Code for RATIONALYST: Pre-training Process-Supervision for Improving Reasoning https://arxiv.org/pdf/2410.01044☆35Updated last year
- ☆134Updated 4 months ago
- ☆25Updated 8 months ago