☆13Jan 14, 2025Updated last year
Alternatives and similar repositories for safety-arithmetic
Users that are interested in safety-arithmetic are comparing it to the libraries listed below
Sorting:
- ☆22Jan 14, 2025Updated last year
- Restore safety in fine-tuned language models through task arithmetic☆32Mar 28, 2024Updated last year
- Code for the EMNLP 2022 Findings short paper "SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Train…☆13Feb 25, 2023Updated 3 years ago
- Domain Adaptation and Adapters☆16Feb 28, 2023Updated 3 years ago
- A Wikipedia-based summarization dataset☆14Mar 27, 2023Updated 2 years ago
- CMIVQA☆18Jun 3, 2024Updated last year
- ControlLM is a method to control the personality traits and behaviors of language models in real-time at inference without costly trainin…☆19Nov 6, 2024Updated last year
- [COLM 2025] "C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing"☆20Apr 9, 2025Updated 11 months ago
- ☆21Aug 8, 2025Updated 7 months ago
- Code and pre-trained models for "ReasonBert: Pre-trained to Reason with Distant Supervision", EMNLP'2021☆29Feb 1, 2023Updated 3 years ago
- Our EMNLP 2022 paper on VIP-Based Prompting for Parameter-Efficient Learning☆10Oct 22, 2022Updated 3 years ago
- Code for our NeurIPS 2024 paper Improved Generation of Adversarial Examples Against Safety-aligned LLMs☆12Nov 7, 2024Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆92May 2, 2025Updated 10 months ago
- [COLM 2025] JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model☆25Nov 25, 2025Updated 3 months ago
- Code for "Distribution-based Emotion Recognition in Conversation"☆19Feb 6, 2023Updated 3 years ago
- The code and data for ACL2021 paper <Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?>☆22Dec 18, 2022Updated 3 years ago
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling☆36Jul 12, 2024Updated last year
- Links to publications that focus on the interpretation and analysis of in-context learning☆15Oct 17, 2024Updated last year
- Unofficial implementation of the Ask-LLM paper 'How to Train Data-Efficient LLMs', arXiv:2402.09668.☆12Jun 19, 2024Updated last year
- Event Relation in Text-to-Audio (TTA) Generation☆20Feb 26, 2025Updated last year
- SPEC-RL: Accelerating On-Policy Reinforcement Learning via Speculative Rollouts☆63Dec 1, 2025Updated 3 months ago
- This repository contains the dataset and baselines explained in the paper: M2H2: A Multimodal Multiparty Hindi Dataset For HumorRecogniti…☆19Mar 14, 2023Updated 3 years ago
- [ICLR 2026] Official Implementation of ProxyThinker: Test-Time Guidance through Small Visual Reasoners.☆20Sep 24, 2025Updated 5 months ago
- Repository for the ACL'22 paper "So Different Yet So Alike! Constrained Unsupervised Text Style Transfer"☆16Jan 19, 2024Updated 2 years ago
- A repo for LLM jailbreak☆14Sep 5, 2023Updated 2 years ago
- Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique☆18Aug 22, 2024Updated last year
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆11Oct 29, 2024Updated last year
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆18Jan 14, 2025Updated last year
- Analyzing LLM Alignment via Token distribution shift☆17Jan 26, 2024Updated 2 years ago
- Code for the COLING 2022 paper "DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification"☆19Oct 19, 2022Updated 3 years ago
- A repository for the EMNLP 2021 paper "Is Information Density Uniform in Task-Oriented Dialogues?" and for the CoNLL 2021 paper "Analysin…☆10Jun 17, 2024Updated last year
- [ICLR 2025] PyTorch Implementation of "ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"☆30Jul 20, 2025Updated 8 months ago
- Official implementation of the paper “Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning”☆20Aug 20, 2025Updated 7 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆22May 6, 2025Updated 10 months ago
- Code for Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation (EVOL-RL).☆48Oct 16, 2025Updated 5 months ago
- Creates CMM script that can directly executed on Kaggle from easy merge script☆14Mar 6, 2026Updated 2 weeks ago
- ☆19Feb 20, 2025Updated last year
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆11Jun 18, 2024Updated last year