[ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
☆32Jan 7, 2026Updated 9 months ago
Alternatives and similar repositories for unintentional-unalignment
Users that are interested in unintentional-unalignment are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Pytorch implementation of the paper 'Compositional language emerge in a neural iterated learning' (ICLR 2020).☆16Oct 14, 2021Updated 5 years ago
- ☆21Nov 4, 2025Updated 11 months ago
- Inverse Scaling in Test-Time Compute☆26Dec 3, 2025Updated 10 months ago
- ☆24Aug 25, 2026Updated 2 months ago
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"☆78Jun 10, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆10Aug 20, 2023Updated 3 years ago
- ☆11Feb 8, 2022Updated 4 years ago
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆32Apr 20, 2024Updated 2 years ago
- Code for the paper "REV: Information-Theoretic Evaluation of Free-Text Rationales"☆16Aug 11, 2023Updated 3 years ago
- ☆10Mar 1, 2024Updated 2 years ago
- IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization☆12Nov 23, 2021Updated 4 years ago
- ☆20Sep 6, 2025Updated last year
- Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)☆62May 12, 2025Updated last year
- ☆46Feb 16, 2022Updated 4 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆14Apr 22, 2024Updated 2 years ago
- Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"☆21Oct 13, 2020Updated 6 years ago
- ☆35May 16, 2025Updated last year
- A collection of papers in fairness of medical image analysis☆13Jun 16, 2023Updated 3 years ago
- [CVPR '26] - PinPoint: Evaluation of Composed Image Retrieval with Explicit Negatives, Multi-Image Queries, and Paraphrase Testing☆15Jun 9, 2026Updated 4 months ago
- ☆14Nov 5, 2024Updated last year
- Self-Supervised Alignment with Mutual Information☆20May 24, 2024Updated 2 years ago
- Code for EMNLP 2021 paper "Measuring Association Between Labels and Free-Text Rationales"☆12Sep 12, 2023Updated 3 years ago
- This repo explores how AMR to address tasks difficult for LLMs☆12Jan 15, 2024Updated 2 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Official implementation of our paper "Benchmarking Language Model Creativity: A Case Study on Code Generation"☆14May 16, 2025Updated last year
- SIGIR 2024, Sequential recommendation, Attribute-Opinions, Fine-grained User and Item Representation.☆13Sep 5, 2024Updated 2 years ago
- Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples☆48Oct 5, 2026Updated 3 weeks ago
- Code and data from the paper 'Human Feedback is not Gold Standard'☆20Aug 9, 2026Updated 2 months ago
- Website for release of TellMeWhy dataset for why question answering☆15Nov 11, 2022Updated 3 years ago
- The official implementation of paper "Can Textual Gradient Work in Federated Learning?" accepted at ICLR 2025☆17Mar 10, 2025Updated last year
- ☆43Sep 3, 2024Updated 2 years ago
- ☆14Nov 15, 2022Updated 3 years ago
- ☆29Feb 17, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [NeurIPS 2024] The implementation of paper "On Softmax Direct Preference Optimization for Recommendation"☆100Nov 29, 2024Updated last year
- ☆11Jun 2, 2022Updated 4 years ago
- ☆80Feb 22, 2024Updated 2 years ago
- [ICML 2025] Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment (https://arxiv.org/abs/2410.02197)☆46Jun 15, 2026Updated 4 months ago
- Deep Weighted Averaging Classifiers☆22Feb 4, 2019Updated 7 years ago
- [ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!☆39Aug 2, 2024Updated 2 years ago
- [ICML2024 Spotlight] Fine-Tuning Pre-trained Large Language Models Sparsely☆24Jun 26, 2024Updated 2 years ago