likenneth / honest_llama
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
☆510Updated last month
Alternatives and similar repositories for honest_llama:
Users that are interested in honest_llama are comparing it to the libraries listed below
- Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"☆472Updated last month
- RewardBench: the first evaluation tool for reward models.☆521Updated 2 weeks ago
- This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large Language Models.☆444Updated last year
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆543Updated last year
- Code and data for "Lost in the Middle: How Language Models Use Long Contexts"☆334Updated last year
- [EMNLP 2023] Adapting Language Models to Compress Long Contexts☆294Updated 6 months ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆805Updated 7 months ago
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them☆468Updated 8 months ago
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆618Updated 7 months ago
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆467Updated last year
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆418Updated 4 months ago
- Data and Code for Program of Thoughts (TMLR 2023)☆263Updated 10 months ago
- OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.☆551Updated last year
- ☆306Updated 9 months ago
- A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.☆350Updated last year
- Learning to Compress Prompts with Gist Tokens - https://arxiv.org/abs/2304.08467☆279Updated last month
- ☆192Updated last year
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆393Updated 9 months ago
- Source code for the paper "Active Prompting with Chain-of-Thought for Large Language Models"☆235Updated 10 months ago
- ☆271Updated 2 months ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆537Updated 3 months ago
- This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.☆506Updated 4 months ago
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆765Updated last year
- Locating and editing factual associations in GPT (NeurIPS 2022)☆605Updated 10 months ago
- Simple next-token-prediction for RLHF☆222Updated last year
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆813Updated this week
- ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels …☆254Updated last year
- A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic…☆325Updated 9 months ago
- This repository provides an original implementation of Detecting Pretraining Data from Large Language Models by *Weijia Shi, *Anirudh Aji…☆218Updated last year
- Generative Judge for Evaluating Alignment☆230Updated last year