AI21Labs / factor
Code and data for the FACTOR paper
☆36Updated 10 months ago
Related projects: ⓘ
- Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models"☆54Updated 8 months ago
- ☆39Updated 9 months ago
- Code and data for paper "Context-faithful Prompting for Large Language Models".☆37Updated last year
- "FiD-ICL: A Fusion-in-Decoder Approach for Efficient In-Context Learning" (ACL 2023)☆13Updated last year
- ☆15Updated last year
- GPT as Human☆17Updated 7 months ago
- Official implementation of the ACL 2023 paper: "Zero-shot Faithful Factual Error Correction"☆17Updated last year
- Official Code for EMNLP2023 Main Conference paper: "KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detec…☆27Updated 10 months ago
- Restore safety in fine-tuned language models through task arithmetic☆25Updated 5 months ago
- ☆44Updated 2 weeks ago
- [EMNLP 2022] Code for our paper “ZeroGen: Efficient Zero-shot Learning via Dataset Generation”.☆15Updated 2 years ago
- ☆32Updated 5 months ago
- ☆32Updated last year
- TBC☆26Updated last year
- [ICLR'24 Spotlight] "Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts"☆51Updated 5 months ago
- Data and code for ACL 2022 paper "MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data"☆41Updated 2 years ago
- The data and the PyTorch implementation for the models and experiments in the paper "Exploiting Asymmetry for Synthetic Training Data Gen…☆56Updated last year
- Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"☆56Updated 6 months ago
- BeHonest: Benchmarking Honesty in Large Language Models☆27Updated last month
- This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.☆38Updated 9 months ago
- Token-level Reference-free Hallucination Detection☆92Updated last year
- ☆32Updated 8 months ago
- Evaluate the Quality of Critique☆35Updated 3 months ago
- This code accompanies the paper DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering.☆17Updated last year
- Code for M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models☆22Updated last month
- First explanation metric (diagnostic report) for text generation evaluation☆59Updated 2 months ago
- Code and Data for NeurIPS2021 Paper "A Dataset for Answering Time-Sensitive Questions"☆61Updated 2 years ago
- [ACL 2024] Code for "MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation"☆29Updated 2 months ago
- ☆78Updated last year
- [NeurIPS 2022] Generating Training Data with Language Models: Towards Zero-Shot Language Understanding☆63Updated 2 years ago