google / sycophancy-interventionLinks
Scripts for generating synthetic finetuning data for reducing sycophancy.
☆117Updated 2 years ago
Alternatives and similar repositories for sycophancy-intervention
Users that are interested in sycophancy-intervention are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2023] This is the code for the paper `Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias`.☆156Updated 2 years ago
- Code and data accompanying our paper on arXiv "Faithful Chain-of-Thought Reasoning".☆165Updated last year
- Self-Alignment with Principle-Following Reward Models☆169Updated 3 months ago
- ☆100Updated last year
- ☆129Updated last year
- Meta-CoT: Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models☆100Updated 2 years ago
- Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]☆149Updated last year
- PASTA: Post-hoc Attention Steering for LLMs☆132Updated last year
- A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs.☆90Updated last year
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆84Updated last year
- ToolBench, an evaluation suite for LLM tool manipulation capabilities.☆167Updated last year
- ☆150Updated last year
- ☆173Updated 2 years ago
- This is the repo for the paper Shepherd -- A Critic for Language Model Generation☆220Updated 2 years ago
- The Official Repository for "Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"☆107Updated 2 years ago
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]☆110Updated 10 months ago
- ☆139Updated last year
- Evaluating LLMs with fewer examples☆170Updated last year
- Simple next-token-prediction for RLHF☆227Updated 2 years ago
- Official Implementation of InstructZero; the first framework to optimize bad prompts of ChatGPT(API LLMs) and finally obtain good prompts…☆197Updated last year
- Scalable Meta-Evaluation of LLMs as Evaluators☆43Updated last year
- Code repo for "Agent Instructs Large Language Models to be General Zero-Shot Reasoners"☆118Updated 2 months ago
- [ACL'24] Code and data of paper "When is Tree Search Useful for LLM Planning? It Depends on the Discriminator"☆54Updated last year
- 🚢 Data Toolkit for Sailor Language Models☆94Updated 9 months ago
- Functional Benchmarks and the Reasoning Gap☆90Updated last year
- Implementation of the paper: "Answering Questions by Meta-Reasoning over Multiple Chains of Thought"☆96Updated last year
- ☆313Updated last year
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆61Updated last year
- ☆159Updated last year
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆226Updated 3 months ago