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.
☆26Dec 3, 2024Updated last year
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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆20Oct 11, 2024Updated last year
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- A TinyStories LM with SAEs and transcoders☆16Aug 19, 2026Updated last month
- ☆25Sep 5, 2024Updated 2 years ago
- Sparse Autoencoder Training Library☆58May 1, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆94Nov 27, 2024Updated last year
- see github.com/understanding-search/maze-transformer☆10Dec 8, 2023Updated 2 years ago
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated 10 months ago
- Engine for collecting, uploading, and downloading model activations☆31Apr 2, 2025Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- Datasets used in the paper "Reward hacking behavior can generalize across tasks"☆16Aug 17, 2025Updated last year
- Creating a game to play Figgie & Train an agent to play against☆15Dec 3, 2022Updated 3 years ago
- ☆26Jun 22, 2025Updated last year
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated 11 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆44Feb 18, 2026Updated 7 months ago
- Repository for the "Chain-of-Thought Reasoning In The Wild Is Not Always Faithful" paper☆35Mar 31, 2026Updated 5 months ago
- ICLR 2025 Workshop & CHI 2025 SIG: "Bidirectional Human-AI Alignment"☆59Aug 6, 2024Updated 2 years ago
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆28Jun 27, 2024Updated 2 years ago
- What's In My Human Feedback? Explaining preferences in human feedback using interpretability + LLMs. https://arxiv.org/abs/2510.26202☆27May 9, 2026Updated 4 months ago
- ☆20Mar 16, 2026Updated 6 months ago
- This repository is associated with the research paper titled ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large…☆15Jun 4, 2025Updated last year
- ☆22Nov 15, 2024Updated last year
- Implementation of path patching & activation patching (will eventually add to TransformerLens).☆15Jan 8, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆50May 31, 2024Updated 2 years ago
- ☆15Mar 30, 2025Updated last year
- Debate interface, experiments, etc.☆12Mar 12, 2024Updated 2 years ago
- ☆11Apr 6, 2023Updated 3 years ago
- Inference API for many LLMs and other useful tools for empirical research☆136May 29, 2026Updated 3 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆275Feb 27, 2026Updated 6 months ago
- Mamba support for transformer lens☆20Sep 17, 2024Updated 2 years ago
- Code for evaluating AI systems on the MASK honesty benchmark.☆26Mar 6, 2025Updated last year
- Distributed Priortized Experience Replay☆10Aug 8, 2018Updated 8 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [2025-TMLR] A Survey on the Honesty of Large Language Models☆66Dec 8, 2024Updated last year
- Track Rust's await bikeshedding☆12Jul 7, 2020Updated 6 years ago
- Functional lenses on C++ (highly experimental).☆10Aug 13, 2019Updated 7 years ago
- Minimum Description Length probing for neural network representations☆20Jan 28, 2025Updated last year
- [ICLR 2025] Weighted-Reward Preference Optimization for Implicit Model Fusion☆14Mar 17, 2025Updated last year
- PyPI package for DualXDA for efficient data attribution and feature-level explanations of training data influence☆22Mar 6, 2026Updated 6 months ago
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆109Nov 10, 2023Updated 2 years ago