princeton-nlp / unintentional-unalignment
[ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
☆24Updated 3 months ago
Alternatives and similar repositories for unintentional-unalignment:
Users that are interested in unintentional-unalignment are comparing it to the libraries listed below
- ☆40Updated last year
- Lightweight Adapting for Black-Box Large Language Models☆22Updated last year
- ☆49Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆53Updated 4 months ago
- Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".☆22Updated 5 months ago
- This is the official repo for Towards Uncertainty-Aware Language Agent.☆24Updated 8 months ago
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆16Updated 3 months ago
- ☆29Updated 11 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated last month
- ☆34Updated 6 months ago
- ☆25Updated 2 years ago
- Directional Preference Alignment☆57Updated 7 months ago
- Extending context length of visual language models☆11Updated 4 months ago
- Augmenting Statistical Models with Natural Language Parameters☆26Updated 7 months ago
- Offical code of the paper Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Le…☆73Updated last year
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆23Updated 9 months ago
- ☆50Updated 2 weeks ago
- Align your LM to express calibrated verbal statements of confidence in its long-form generations.☆22Updated 10 months ago
- Methods and evaluation for aligning language models temporally☆29Updated last year
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 7 months ago
- ☆18Updated last year
- The official repository of "Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint"☆38Updated last year
- AbstainQA, ACL 2024☆25Updated 6 months ago
- The code of “Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning”☆16Updated last year
- ☆22Updated 6 months ago
- ☆73Updated 11 months ago
- ☆14Updated last year
- GenRM-CoT: Data release for verification rationales☆56Updated 6 months ago
- Rewarded soups official implementation☆58Updated last year
- ☆13Updated last year