princeton-nlp / unintentional-unalignmentLinks
[ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
☆28Updated 4 months ago
Alternatives and similar repositories for unintentional-unalignment
Users that are interested in unintentional-unalignment are comparing it to the libraries listed below
Sorting:
- ☆40Updated last year
- Lightweight Adapting for Black-Box Large Language Models☆22Updated last year
- ☆29Updated last year
- ☆49Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆58Updated 6 months ago
- Directional Preference Alignment☆56Updated 8 months ago
- ☆44Updated 2 years ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 8 months ago
- Augmenting Statistical Models with Natural Language Parameters☆26Updated 8 months ago
- Methods and evaluation for aligning language models temporally☆29Updated last year
- ☆74Updated last year
- Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".☆23Updated 7 months ago
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆16Updated 4 months ago
- This is the official repo for Towards Uncertainty-Aware Language Agent.☆25Updated 9 months ago
- ☆51Updated last month
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆31Updated 8 months ago
- code for EMNLP 2024 paper: How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for M…☆11Updated 6 months ago
- ☆13Updated 5 months ago
- ☆27Updated 2 years ago
- ☆94Updated last year
- Align your LM to express calibrated verbal statements of confidence in its long-form generations.☆25Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 2 months ago
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆58Updated 2 months ago
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆77Updated 5 months ago