likenneth / honest_llama
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
☆513Updated last month
Alternatives and similar repositories for honest_llama:
Users that are interested in honest_llama are comparing it to the libraries listed below
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆469Updated last year
- Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"☆473Updated 2 months ago
- RewardBench: the first evaluation tool for reward models.☆522Updated 3 weeks ago
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆543Updated last year
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them☆469Updated 8 months ago
- This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large Language Models.☆446Updated last year
- 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
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆393Updated 10 months ago
- Code and data for "Lost in the Middle: How Language Models Use Long Contexts"☆334Updated last year
- ☆193Updated last year
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆619Updated 7 months ago
- Locating and editing factual associations in GPT (NeurIPS 2022)☆606Updated 11 months ago
- [EMNLP 2023] Adapting Language Models to Compress Long Contexts☆295Updated 6 months ago
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆420Updated 5 months ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆806Updated 7 months ago
- Simple next-token-prediction for RLHF☆222Updated last year
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆765Updated last year
- [EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627☆477Updated 5 months ago
- [ACL'24 Outstanding] Data and code for L-Eval, a comprehensive long context language models evaluation benchmark☆371Updated 8 months ago
- DSIR large-scale data selection framework for language model training☆243Updated 11 months ago
- Data and Code for Program of Thoughts (TMLR 2023)☆263Updated 10 months ago
- [EMNLP 2023] The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning☆234Updated last year
- Code for STaR: Bootstrapping Reasoning With Reasoning (NeurIPS 2022)☆203Updated 2 years ago
- ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings - NeurIPS 2023 (oral)☆259Updated 11 months ago
- Generative Judge for Evaluating Alignment☆230Updated last year
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆801Updated 8 months ago
- Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets☆313Updated last year
- OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.☆552Updated last year
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆540Updated 3 months ago