PrasannS / rlhf-length-biasesLinks
☆27Updated last year
Alternatives and similar repositories for rlhf-length-biases
Users that are interested in rlhf-length-biases are comparing it to the libraries listed below
Sorting:
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training☆22Updated last year
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆39Updated 2 years ago
- [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…☆52Updated last year
- Unofficial implementation of Chain of Hindsight (https://arxiv.org/abs/2302.02676) using pytorch and huggingface Trainers.☆11Updated 2 years ago
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆63Updated last year
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging☆108Updated last year
- ☆11Updated last year
- ☆86Updated 2 years ago
- Repository for "Scaling Evaluation-time Compute with Reasoning Models as Process Evaluators"☆12Updated 6 months ago
- ☆19Updated 2 years ago
- [ACL 2023 Findings] What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning☆21Updated 2 years ago
- Directional Preference Alignment☆57Updated last year
- ☆44Updated last year
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆80Updated last year
- This repository contains data, code and models for contextual noncompliance.☆24Updated last year
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…☆32Updated last year
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆97Updated 4 years ago
- Teaching Models to Express Their Uncertainty in Words☆39Updated 3 years ago
- ☆54Updated last year
- Benchmarking Benchmark Leakage in Large Language Models☆55Updated last year
- Introducing Filtered Direct Preference Optimization (fDPO) that enhances language model alignment with human preferences by discarding lo…☆16Updated 10 months ago
- ☆22Updated 2 years ago
- [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages☆50Updated last month
- DEMix Layers for Modular Language Modeling☆54Updated 4 years ago
- ☆64Updated 2 years ago
- ☆75Updated last year
- ☆49Updated 2 years ago
- [AAAI 2024] Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following☆78Updated last year
- The git repository of Modular Prompted Chatbot paper☆35Updated 2 years ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆75Updated 4 months ago