ContextualAI / CLAIR_and_APOLinks
Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
☆61Updated last year
Alternatives and similar repositories for CLAIR_and_APO
Users that are interested in CLAIR_and_APO are comparing it to the libraries listed below
Sorting:
- ☆55Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆45Updated 4 months ago
- A repository for research on medium sized language models.☆77Updated last year
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆31Updated 7 months ago
- ☆91Updated last year
- [TMLR 2026] When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models☆121Updated 11 months ago
- ☆17Updated 9 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆94Updated last year
- Aioli: A unified optimization framework for language model data mixing☆32Updated last year
- ReBase: Training Task Experts through Retrieval Based Distillation☆29Updated 11 months ago
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆45Updated 2 years ago
- The repository contains code for Adaptive Data Optimization☆32Updated last year
- Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"☆91Updated last year
- ☆91Updated last month
- Verifiers for LLM Reinforcement Learning☆80Updated 9 months ago
- Code for RATIONALYST: Pre-training Process-Supervision for Improving Reasoning https://arxiv.org/pdf/2410.01044☆35Updated last year
- ☆41Updated last year
- ☆129Updated last year
- EMNLP 2024 "Re-reading improves reasoning in large language models". Simply repeating the question to get bidirectional understanding for…☆28Updated last year
- Learning to Retrieve by Trying - Source code for Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval☆51Updated last year
- An automated data pipeline scaling RL to pretraining levels☆73Updated 3 months ago
- Codebase accompanying the Summary of a Haystack paper.☆80Updated last year
- ☆123Updated 11 months ago
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated 2 years ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated 2 years ago
- MEXMA: Token-level objectives improve sentence representations☆42Updated last year
- Implementation of "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"☆40Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆78Updated last year
- ☆48Updated last year
- ☆23Updated last year