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 2 years ago
- A TinyStories LM with SAEs and transcoders☆16Aug 19, 2026Updated 3 months ago
- ☆27Sep 5, 2024Updated 2 years ago
- ☆16Oct 3, 2024Updated 2 years ago
- see github.com/understanding-search/maze-transformer☆10Dec 8, 2023Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Highlight errors in a bib file: missing URLs, capitalization protection, etc☆29May 12, 2024Updated 2 years ago
- Chess agent specification gaming☆25Updated this week
- ☆25Jun 30, 2025Updated last year
- Engine for collecting, uploading, and downloading model activations☆31Apr 2, 2025Updated last year
- ☆36Nov 11, 2026Updated last week
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- ☆15Nov 7, 2026Updated last week
- 🌳 Repository for the "Thought Branches: Interpreting LLM Reasoning Requires Resampling" paper.☆14Nov 5, 2025Updated last year
- Repo for HAICOSYSTEM☆14Jun 1, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆10Aug 29, 2021Updated 5 years ago
- Improving transparency of large language models' reasoning☆15Nov 25, 2025Updated 11 months ago
- ☆27Jun 22, 2025Updated last year
- Code for "On Measuring Faithfulness of Natural Language Explanations"☆23Jul 14, 2026Updated 4 months ago
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated last year
- ☆10Oct 11, 2022Updated 4 years ago
- ☆47Feb 18, 2026Updated 9 months ago
- Using randomized hill climbing to parameterize a PID Control solution to Lunar Lander☆12Jul 30, 2017Updated 9 years ago
- LXM3: XManager launch backend for HPC clusters☆11May 11, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Repository for the "Chain-of-Thought Reasoning In The Wild Is Not Always Faithful" paper☆36Mar 31, 2026Updated 7 months ago
- Custom graph/network/multi-weighted network class based on storing list of neighbors for each nodes (as opposed to edge list) for scalabl…☆11Jan 18, 2024Updated 2 years ago
- Codes for paper: "LaMP-QA: A Benchmark for Personalized Long-form Question Answering"☆13Jun 3, 2025Updated last year
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆34Jan 23, 2025Updated last year
- Evaluating Agents under Ambiguous settings for SWE tasks☆22Sep 21, 2026Updated last month
- Generate realistic and diverse user personas for LLM agent benchmarks.☆13Oct 18, 2026Updated last month
- A library for efficient patching and automatic circuit discovery.☆103Aug 17, 2026Updated 3 months ago
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆29Jun 27, 2024Updated 2 years ago
- ☆12Aug 26, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆12Oct 27, 2024Updated 2 years ago
- ☆17May 21, 2026Updated 5 months ago
- ☆16Sep 4, 2023Updated 3 years ago
- ☆22Nov 15, 2024Updated 2 years ago
- Dealing with Flags and Options☆13Oct 29, 2026Updated 3 weeks ago
- Track Rust's await bikeshedding☆12Jul 7, 2020Updated 6 years ago
- tart: tensor abstracted relations and topologies☆12Jul 5, 2024Updated 2 years ago
Are these results useful?