BunsenFeng / modular_pluralism
Modular Pluralism @ EMNLP 2024
☆17Updated 7 months ago
Alternatives and similar repositories for modular_pluralism:
Users that are interested in modular_pluralism are comparing it to the libraries listed below
- A resource repository for representation engineering in large language models☆119Updated 5 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆144Updated 11 months ago
- ☆93Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆74Updated last year
- ☆164Updated 10 months ago
- Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".☆22Updated 5 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆53Updated 5 months ago
- ☆18Updated last year
- This repo contains code for our NeurIPS 2023 spotlight paper: Evaluating and Inducing Personality in Pre-trained Language Models☆52Updated last year
- Public code repo for COLING 2025 paper "Aligning LLMs with Individual Preferences via Interaction"☆26Updated 3 weeks ago
- ☆13Updated 5 months ago
- ☆48Updated last year
- ☆40Updated last year
- The Prism Alignment Project☆75Updated last year
- Algebraic value editing in pretrained language models☆63Updated last year
- UnQovering Stereotyping Biases via Underspecified Questions - EMNLP 2020 (Findings)☆22Updated 3 years ago
- Official Code Repository for LM-Steer Paper: "Word Embeddings Are Steers for Language Models" (ACL 2024 Outstanding Paper Award)☆99Updated 6 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆161Updated last week
- A library for efficient patching and automatic circuit discovery.☆62Updated 2 months ago
- ☆61Updated last year
- ☆21Updated 5 months ago
- How do transformer LMs encode relations?☆47Updated last year
- Official reposity for paper "High-Dimension Human Value Representation in Large Language Models"☆23Updated 9 months ago
- ☆29Updated 11 months ago
- General-purpose activation steering library☆61Updated 3 months ago
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆60Updated last year
- ☆38Updated last year
- ☆27Updated last month
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆91Updated last year