marcus-jw / Targeted-Manipulation-and-Deception-in-LLMsLinks
Codebase for "On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback". This repo implements a generative multi-turn RL environment with support for agent, user, user feedback, transition and veto models. It also implements KTO and expert iteration for training on user preferences.
☆22Updated 11 months ago
Alternatives and similar repositories for Targeted-Manipulation-and-Deception-in-LLMs
Users that are interested in Targeted-Manipulation-and-Deception-in-LLMs are comparing it to the libraries listed below
Sorting:
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆18Updated last year
- A library for efficient patching and automatic circuit discovery.☆80Updated 4 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆36Updated last month
- A TinyStories LM with SAEs and transcoders☆13Updated 7 months ago
- ☆24Updated last year
- Sparse Autoencoder Training Library☆55Updated 6 months ago
- ☆94Updated last year
- ☆23Updated last year
- ☆16Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Updated 11 months ago
- ☆23Updated 9 months ago
- ☆32Updated 9 months ago
- Measuring the situational awareness of language models☆39Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆42Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- ☆129Updated last year
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆28Updated 3 weeks ago
- Code for "Reasoning to Learn from Latent Thoughts"☆122Updated 7 months ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆50Updated 11 months ago
- Algebraic value editing in pretrained language models☆66Updated 2 years ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆141Updated 4 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆121Updated last year
- Universal Neurons in GPT2 Language Models☆31Updated last year
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆47Updated last year
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆26Updated 9 months ago
- ☆20Updated last year
- Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)☆29Updated last month
- Rewarded soups official implementation☆62Updated 2 years ago
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆32Updated last year