y0mingzhang / diffuse-distributionsLinks
Forcing Diffuse Distributions out of Language Models
☆16Updated 9 months ago
Alternatives and similar repositories for diffuse-distributions
Users that are interested in diffuse-distributions are comparing it to the libraries listed below
Sorting:
- Augmenting Statistical Models with Natural Language Parameters☆27Updated 9 months ago
- ☆40Updated last year
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆11Updated 5 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 3 months ago
- ☆12Updated last year
- ☆29Updated last year
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- Official repository for ICLR 2024 Spotlight paper "Large Language Models Are Not Robust Multiple Choice Selectors"☆39Updated last month
- ☆37Updated last year
- ☆44Updated last year
- ☆95Updated last year
- ☆35Updated last month
- This repository contains data, code and models for contextual noncompliance.☆23Updated 11 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆60Updated 7 months ago
- ☆13Updated 7 months ago
- Align your LM to express calibrated verbal statements of confidence in its long-form generations.☆26Updated last year
- Code for the paper "A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis"☆18Updated 2 weeks ago
- Analyzing LLM Alignment via Token distribution shift☆16Updated last year
- ☆62Updated 2 years ago
- ☆14Updated last year
- ☆48Updated last year
- ☆49Updated last year
- [ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization☆29Updated 5 months ago
- ☆51Updated 2 months ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆27Updated last year
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆44Updated 2 months ago
- ☆48Updated last month
- Revisiting Mid-training in the Era of RL Scaling☆62Updated 2 months ago
- BeHonest: Benchmarking Honesty in Large Language Models☆34Updated 10 months ago
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆17Updated last year