tml-epfl / long-is-more-for-alignment
Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]
☆17Updated 8 months ago
Alternatives and similar repositories for long-is-more-for-alignment:
Users that are interested in long-is-more-for-alignment are comparing it to the libraries listed below
- ☆34Updated 11 months ago
- Restore safety in fine-tuned language models through task arithmetic☆26Updated 9 months ago
- ☆29Updated 8 months ago
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆22Updated 3 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆61Updated 2 months ago
- ☆27Updated 2 months ago
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆74Updated last year
- Test-time-training on nearest neighbors for large language models☆37Updated 9 months ago
- Is In-Context Learning Sufficient for Instruction Following in LLMs?☆26Updated 7 months ago
- Analyzing LLM Alignment via Token distribution shift☆14Updated 11 months ago
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆55Updated 6 months ago
- The code of “Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning”☆15Updated 10 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆41Updated 5 months ago
- Directional Preference Alignment☆54Updated 3 months ago
- ☆19Updated last year
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆42Updated last month
- Codebase for decoding compressed trust.☆22Updated 8 months ago
- ☆36Updated last year
- ☆29Updated 8 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆30Updated this week
- Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".☆18Updated 2 months ago
- Code for "Universal Adversarial Triggers Are Not Universal."☆16Updated 8 months ago
- ☆21Updated 6 months ago
- ☆25Updated last year
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆63Updated 6 months ago
- ☆44Updated 4 months ago
- [EMNLP Findings 2024 & ACL 2024 NLRSE Oral] Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards☆49Updated 8 months ago
- ☆85Updated last year
- Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning with LLMs☆32Updated 11 months ago
- ☆63Updated 2 years ago