kmeng01 / romeLinks
Locating and editing factual associations in GPT (NeurIPS 2022)
☆653Updated last year
Alternatives and similar repositories for rome
Users that are interested in rome are comparing it to the libraries listed below
Sorting:
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆539Updated 6 months ago
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆509Updated last year
- Representation Engineering: A Top-Down Approach to AI Transparency☆852Updated 11 months ago
- ☆220Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆512Updated last year
- TruthfulQA: Measuring How Models Imitate Human Falsehoods☆781Updated 6 months ago
- This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large Language Models.☆497Updated last year
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them☆504Updated last year
- Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"☆504Updated 6 months ago
- A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.☆372Updated last year
- ☆239Updated 2 years ago
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆546Updated last year
- ☆503Updated last year
- Code and data for "Lost in the Middle: How Language Models Use Long Contexts"☆352Updated last year
- A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic…☆366Updated 3 months ago
- Accompanying repo for the RLPrompt paper☆341Updated last year
- Prod Env☆424Updated last year
- Learning to Compress Prompts with Gist Tokens - https://arxiv.org/abs/2304.08467☆289Updated 5 months ago
- RewardBench: the first evaluation tool for reward models.☆619Updated last month
- Expanding natural instructions☆1,010Updated last year
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆769Updated 2 years ago
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆261Updated last year
- ☆154Updated 8 months ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆873Updated 3 weeks ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆783Updated last week
- OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.☆569Updated last year
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆141Updated last week
- ☆291Updated last year
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆474Updated 9 months ago