[ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
☆32Jan 7, 2026Updated 10 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:
- ☆16Sep 29, 2026Updated last month
- [NeurIPS 2025] What Makes a Reward Model a Good Teacher? An Optimization Perspective☆45Sep 18, 2025Updated last year
- Pytorch implementation of the paper 'Compositional language emerge in a neural iterated learning' (ICLR 2020).☆16Oct 14, 2021Updated 5 years ago
- ☆15Mar 30, 2025Updated last year
- ☆24Aug 25, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆10Aug 20, 2023Updated 3 years 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
- ☆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
- IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization☆12Nov 23, 2021Updated 4 years ago
- Code for the paper "LongKey: Keyphrase Extraction for Long Documents"☆11Nov 28, 2024Updated last year
- Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)☆63May 12, 2025Updated last year
- On the pitfalls of measuring emergent communication☆35Mar 12, 2019Updated 7 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 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
- ☆46Feb 16, 2022Updated 4 years ago
- ☆15Nov 7, 2026Updated last week
- ☆20Sep 6, 2025Updated last year
- ☆14Apr 22, 2024Updated 2 years ago
- ☆14Nov 5, 2024Updated 2 years ago
- Self-Supervised Alignment with Mutual Information☆20May 24, 2024Updated 2 years ago
- Latent Space Smoothing for Individually Fair Representations (ECCV 2022)☆15Nov 4, 2022Updated 4 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Official implementation of our paper "Benchmarking Language Model Creativity: A Case Study on Code Generation"☆14May 16, 2025Updated last year
- [ACL 2026] Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers☆15Jun 3, 2026Updated 5 months ago
- [COLM 2026] Official codebase of paper "Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Followi…☆13Nov 5, 2026Updated 2 weeks ago
- Codes for my numerical methods for PDE course☆12Mar 31, 2026Updated 7 months ago
- Code and data from the paper 'Human Feedback is not Gold Standard'☆21Aug 9, 2026Updated 3 months ago
- This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.☆45Dec 15, 2023Updated 2 years ago
- Harness-Delta Attribution: Dissecting Gains From Harness Evolution☆16Oct 19, 2026Updated 3 weeks ago
- The official implementation of paper "Can Textual Gradient Work in Federated Learning?" accepted at ICLR 2025☆17Mar 10, 2025Updated last year
- ☆14Jun 5, 2025Updated last year
- 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.
- Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples☆48Oct 5, 2026Updated last month
- ☆80Feb 22, 2024Updated 2 years ago
- ☆29Feb 17, 2024Updated 2 years ago
- [ICML 2025] Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment (https://arxiv.org/abs/2410.02197)☆46Nov 5, 2026Updated 2 weeks ago
- [ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!☆39Aug 2, 2024Updated 2 years ago
- Website for release of TellMeWhy dataset for why question answering☆15Nov 11, 2022Updated 4 years ago
- [NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example☆453Mar 11, 2026Updated 8 months ago
Are these results useful?