zepingyu0512 / neuron-attribution
code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models
☆31Updated 5 months ago
Alternatives and similar repositories for neuron-attribution:
Users that are interested in neuron-attribution are comparing it to the libraries listed below
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆53Updated 5 months ago
- ☆29Updated 11 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆37Updated 3 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆57Updated last year
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆67Updated 2 years ago
- awesome SAE papers☆26Updated 2 months ago
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆23Updated 10 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆109Updated last year
- ☆41Updated last year
- ☆27Updated last month
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆109Updated 7 months ago
- ☆42Updated 5 months ago
- Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"☆63Updated last year
- A versatile toolkit for applying Logit Lens to modern large language models (LLMs). Currently supports Llama-3.1-8B and Qwen-2.5-7B, enab…☆75Updated 2 months ago
- ☆57Updated 9 months ago
- ☆21Updated last month
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆72Updated 6 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated last month
- Evaluating the Ripple Effects of Knowledge Editing in Language Models☆55Updated last year
- ☆34Updated 2 months ago
- BeHonest: Benchmarking Honesty in Large Language Models☆31Updated 8 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆76Updated 3 weeks ago
- ☆10Updated 2 months ago
- ☆38Updated last year
- ☆24Updated 2 years ago
- ☆73Updated 11 months ago
- ☆21Updated 4 months ago
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated 2 months ago
- [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".☆76Updated 3 months ago
- [NeurIPS 2024] How do Large Language Models Handle Multilingualism?☆32Updated 5 months ago