[ACL 2025] Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms
☆43Jun 4, 2025Updated last year
Alternatives and similar repositories for steer-target-atoms
Users that are interested in steer-target-atoms are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Implement of Implicit Knowledge Extraction Attack.☆25Jul 14, 2026Updated 3 months ago
- ☆98Mar 28, 2025Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆254May 23, 2024Updated 2 years ago
- Just collections of notebooks playing around diffusion models.☆13Nov 20, 2022Updated 3 years ago
- ☆18Aug 19, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [ACL 2023] TeAST: Temporal Knowledge Graph Embedding via Archimedean Spiral Timeline☆12Mar 4, 2024Updated 2 years ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 4 months ago
- Official code for our paper "SoK: Large Language Model Copyright Auditing via Fingerprinting"☆20Dec 31, 2025Updated 9 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆218Mar 12, 2026Updated 7 months ago
- Source code for the ACL'2025 paper titled "Unveiling privacy risks in llm agent memory"☆37Dec 2, 2025Updated 10 months ago
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging☆123Oct 23, 2023Updated 2 years ago
- ☆23Sep 28, 2023Updated 3 years ago
- Code for our NAACL2025 accepted paper: Attention Tracker: Detecting Prompt Injection Attacks in LLMs☆33Sep 19, 2025Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆117Sep 27, 2024Updated 2 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.
- ☆15Nov 29, 2025Updated 10 months ago
- Landing page for MIB: A Mechanistic Interpretability Benchmark☆27Aug 15, 2025Updated last year
- Experiments on continuous LMs.☆18May 12, 2025Updated last year
- ☆36Feb 27, 2025Updated last year
- PIForge: An Open Framework for RL-based Prompt Injection Red Teaming.☆35Sep 30, 2026Updated 2 weeks ago
- ☆48May 29, 2026Updated 4 months ago
- ☆12Jan 10, 2025Updated last year
- ICL backdoor attack☆17Nov 4, 2024Updated last year
- Causal Inference-based Debiasing Framework for Knowledge Graph Completion☆14Mar 19, 2024Updated 2 years ago
- 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.
- Review your thesis from the perspective of a reviewer. Distilling Years of Experience from a University Instructor.☆14May 3, 2026Updated 5 months ago
- PyTorch implementation of StableMask (ICML'24)☆15Jun 27, 2024Updated 2 years ago
- ☆24Dec 8, 2024Updated last year
- ☆23Sep 2, 2025Updated last year
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆308Jan 22, 2026Updated 8 months ago
- [ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliabilit…☆35Feb 5, 2026Updated 8 months ago
- [NAACL 2025] Representing Rule-based Chatbots with Transformers☆23Feb 9, 2025Updated last year
- PyTorch code for our paper "AdaSVD: Adaptive Singular Value Decomposition for Large Language Models"☆16Mar 9, 2025Updated last year
- Implementation code for ACL2024：Advancing Parameter Efficiency in Fine-tuning via Representation Editing☆15Apr 20, 2024Updated 2 years ago
- 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.
- BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically i…☆50Mar 16, 2026Updated 6 months ago
- [ICML 2024] Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization☆17May 12, 2024Updated 2 years ago
- MiSS is a novel PEFT method that features a low-rank structure but introduces a new update mechanism distinct from LoRA, achieving an exc…☆36Mar 9, 2026Updated 7 months ago
- [ICLR 2026] Official implementation of "ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents"☆26Mar 23, 2026Updated 6 months ago
- ☆79Mar 6, 2025Updated last year
- A curated lists of self-taught materials including research blogs☆16Dec 12, 2016Updated 9 years ago
- Code for Reducing Hallucinations in Vision-Language Models via Latent Space Steering☆120Nov 23, 2024Updated last year