ContextualAI / CLAIR_and_APOLinks
Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
☆60Updated 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 11 months ago
- ReBase: Training Task Experts through Retrieval Based Distillation☆29Updated 8 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆43Updated 3 weeks ago
- ☆128Updated last year
- A repository for research on medium sized language models.☆78Updated last year
- ☆80Updated last week
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"☆90Updated last year
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆44Updated last year
- EMNLP 2024 "Re-reading improves reasoning in large language models". Simply repeating the question to get bidirectional understanding for…☆27Updated 10 months ago
- ☆86Updated last year
- Verifiers for LLM Reinforcement Learning☆76Updated 6 months ago
- Codebase accompanying the Summary of a Haystack paper.☆79Updated last year
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆59Updated last year
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆28Updated 2 years ago
- [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages☆51Updated 2 months ago
- This is the official repository for Inheritune.☆115Updated 8 months ago
- MEXMA: Token-level objectives improve sentence representations☆41Updated 9 months ago
- Aioli: A unified optimization framework for language model data mixing☆27Updated 9 months ago
- Code for RATIONALYST: Pre-training Process-Supervision for Improving Reasoning https://arxiv.org/pdf/2410.01044☆35Updated last year
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆92Updated 11 months ago
- ☆57Updated last year
- The repository contains code for Adaptive Data Optimization☆26Updated 10 months ago
- ☆83Updated this week
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"