tonychenxyz / selfie
This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen, Carl Vondrick, and Chengzhi Mao.
☆48Updated 4 months ago
Alternatives and similar repositories for selfie:
Users that are interested in selfie are comparing it to the libraries listed below
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆57Updated last year
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆108Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆161Updated last week
- What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective☆63Updated last month
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 7 months ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆115Updated last month
- ☆68Updated 3 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆28Updated last month
- ☆157Updated 3 weeks ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated last month
- ☆30Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆76Updated 3 weeks ago
- A Survey on the Honesty of Large Language Models☆57Updated 4 months ago
- ☆44Updated 5 months ago
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆67Updated 2 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆53Updated 5 months ago
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆30Updated 5 months ago
- ☆37Updated last year
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆60Updated 4 months ago
- General-purpose activation steering library☆61Updated 3 months ago
- Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering☆57Updated 4 months ago
- [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…☆49Updated 11 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆77Updated 6 months ago
- ☆27Updated 10 months ago
- Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting☆32Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆35Updated 5 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆103Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆91Updated 11 months ago
- Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"☆74Updated 10 months ago
- ☆54Updated last week