[ICLR 2025] Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron
☆36Apr 30, 2025Updated last year
Alternatives and similar repositories for Safety-Neuron
Users that are interested in Safety-Neuron 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] The implementation of paper "The Emergence of Abstract Thought in Large Language Models Beyond Any Language"☆20Jun 9, 2025Updated last year
- Code for the paper "AsFT: Anchoring Safety During LLM Fune-Tuning Within Narrow Safety Basin".☆38Jul 10, 2025Updated last year
- Confidence Regulation Neurons in Language Models (NeurIPS 2024)☆16Feb 1, 2025Updated last year
- ☆42Jul 3, 2026Updated 2 months ago
- [NeurIPS 2024] How do Large Language Models Handle Multilingualism?☆52Nov 8, 2024Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆36Jun 13, 2025Updated last year
- Code for SafeMERGE (ICLR 2025).☆15Apr 1, 2025Updated last year
- Data and code for the paper: Finding Safety Neurons in Large Language Models☆31Jan 29, 2026Updated 7 months ago
- ☆16Aug 22, 2026Updated 2 weeks ago
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆25May 20, 2025Updated last year
- Introduce a continuous intermediate representation between "masks" and "tokens" for dLLM☆15Dec 1, 2025Updated 9 months ago
- XoRL☆46Updated this week
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆21Mar 22, 2026Updated 5 months ago
- The official code repo for "Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets" in ICML 2025.☆59Feb 12, 2026Updated 6 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints☆19May 23, 2025Updated last year
- [COLM 2026] Official implementation for "MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Mo…☆21Updated this week
- ☆79Mar 6, 2025Updated last year
- Official code for the paper "Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?" (ICLR 2024)☆11Aug 26, 2024Updated 2 years ago
- Benchmarking Dark Patterns in LLMs (ICLR 2025)☆18Mar 29, 2025Updated last year
- Design for Error Detection in Deep-Research Agents Trajectories.☆23Jun 4, 2026Updated 3 months ago
- [ICLR 2025] Official implementation of paper "Dynamic Low-Rank Sparse Adaptation for Large Language Models".☆25Mar 16, 2025Updated last year
- [ICML 2023] "NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations" by Yonggan …☆19Mar 10, 2024Updated 2 years ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆91Mar 30, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆83Mar 30, 2025Updated last year
- ☆71Jun 1, 2025Updated last year
- [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆39Aug 20, 2025Updated last year
- ☆11Apr 2, 2024Updated 2 years ago
- ☆45May 29, 2026Updated 3 months ago
- ☆12Sep 28, 2023Updated 2 years ago
- Focused Papers, Delivered Simply ：）☆55Dec 25, 2025Updated 8 months ago
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆35Jul 31, 2026Updated last month
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆434Jun 13, 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.
- ☆11Oct 15, 2024Updated last year
- ☆12Jun 5, 2024Updated 2 years ago
- This repo is the official implementation of “Are Your Agents Upward Deceivers?”. The paper is accepted by ICML 2026.☆24Dec 15, 2025Updated 8 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆38Nov 2, 2024Updated last year
- [NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient☆67Sep 27, 2025Updated 11 months ago
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbre…☆62Jul 5, 2025Updated last year
- Official Implementation of MULTI-LANE (Multi Label class incremental learning via summarising pAtch tokeN Embeddings). Published in 3rd C…☆15Feb 20, 2025Updated last year