[ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
☆32Jan 7, 2026Updated 7 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:
- [NeurIPS 2025] What Makes a Reward Model a Good Teacher? An Optimization Perspective☆45Sep 18, 2025Updated 11 months ago
- Pytorch implementation of the paper 'Compositional language emerge in a neural iterated learning' (ICLR 2020).☆16Oct 14, 2021Updated 4 years ago
- Inverse Scaling in Test-Time Compute☆26Dec 3, 2025Updated 8 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
- ☆23Updated this week
- 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 the paper "REV: Information-Theoretic Evaluation of Free-Text Rationales"☆16Aug 11, 2023Updated 3 years ago
- ☆18Sep 6, 2025Updated 11 months ago
- Code for Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning☆38Jun 16, 2024Updated 2 years ago
- On the pitfalls of measuring emergent communication☆34Mar 12, 2019Updated 7 years ago
- Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"☆21Oct 13, 2020Updated 5 years ago
- Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples☆47Jul 16, 2025Updated last year
- Self-Supervised Alignment with Mutual Information☆20May 24, 2024Updated 2 years ago
- Website for release of TellMeWhy dataset for why question answering☆14Nov 11, 2022Updated 3 years ago
- ☆14Nov 15, 2022Updated 3 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.
- This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.☆44Dec 15, 2023Updated 2 years ago
- This repo explores how AMR to address tasks difficult for LLMs☆12Jan 15, 2024Updated 2 years ago
- Code for EMNLP 2021 paper "Measuring Association Between Labels and Free-Text Rationales"☆12Sep 12, 2023Updated 2 years ago
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆101Aug 20, 2024Updated 2 years ago
- Deep Weighted Averaging Classifiers☆22Feb 4, 2019Updated 7 years ago
- Code and data from the paper 'Human Feedback is not Gold Standard'☆20Aug 9, 2026Updated 3 weeks ago
- ☆43Sep 3, 2024Updated last year
- ☆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)☆44Jun 15, 2026Updated 2 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- [EMNLP 2024] Enhancing High-order Interaction Awareness in LLM-based Recommender Model.☆13Jan 9, 2025Updated last year
- The official implementation of "ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimization…☆16Feb 15, 2024Updated 2 years ago
- [ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!☆39Aug 2, 2024Updated 2 years ago
- A repository to introduce the algorithmic information theory. You could learn what is Kolmogorov complexity and why it is important here.☆13Jul 23, 2025Updated last year
- ☆11Jun 2, 2022Updated 4 years ago
- [ICML2024 Spotlight] Fine-Tuning Pre-trained Large Language Models Sparsely☆24Jun 26, 2024Updated 2 years ago
- A package containing utils for the PyTorch version of the Tapas algorithm.☆11Apr 29, 2021Updated 5 years ago
- ☆26Nov 8, 2022Updated 3 years ago
- ☆20Dec 16, 2020Updated 5 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A zero-shot faithfulness evaluation metric for text summarization☆11Oct 17, 2023Updated 2 years ago
- Code for Cached Long Short-Term Memory Neural Networks for Document-Level Sentiment Classification☆12Nov 22, 2017Updated 8 years ago
- Wenzhou-Kean University AI-LAB☆10Jun 6, 2022Updated 4 years ago
- Throughput-oriented multi-turn inference engine for KernelBench [ICML '25]☆24May 27, 2025Updated last year
- Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)☆59May 12, 2025Updated last year
- ☆34Nov 21, 2023Updated 2 years ago
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆30Oct 14, 2025Updated 10 months ago