tonychenxyz / selfieLinks
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.
☆51Updated 9 months ago
Alternatives and similar repositories for selfie
Users that are interested in selfie are comparing it to the libraries listed below
Sorting:
- Function Vectors in Large Language Models (ICLR 2024)☆179Updated 5 months ago
- Official Code Repository for LM-Steer Paper: "Word Embeddings Are Steers for Language Models" (ACL 2024 Outstanding Paper Award)☆125Updated 2 months ago
- [NeurIPS 2024] Knowledge Circuits in Pretrained Transformers☆157Updated 6 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆128Updated 2 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆116Updated last year
- [COLING'25] Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?☆80Updated 7 months ago
- ☆190Updated 5 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆118Updated last year
- ☆77Updated 7 months ago
- ☆34Updated last year
- FeatureAlignment = Alignment + Mechanistic Interpretability☆29Updated 6 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆146Updated last week
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆63Updated 9 months ago
- Steering Llama 2 with Contrastive Activation Addition☆180Updated last year
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆186Updated 7 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆61Updated last year
- [ACL'25 Oral] What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective☆72Updated 2 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆39Updated 10 months ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆127Updated 5 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆97Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆111Updated 6 months ago
- ☆97Updated last year
- Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering☆61Updated 9 months ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆106Updated last month
- Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting☆33Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆95Updated last year
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆123Updated last year
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆42Updated 10 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆82Updated 10 months ago
- PASTA: Post-hoc Attention Steering for LLMs☆122Updated 9 months ago