yxuansu / Contrastive_Search_Is_What_You_Need
[TMLR'23] Contrastive Search Is What You Need For Neural Text Generation
☆119Updated 2 years ago
Alternatives and similar repositories for Contrastive_Search_Is_What_You_Need:
Users that are interested in Contrastive_Search_Is_What_You_Need are comparing it to the libraries listed below
- Official code and model checkpoints for our EMNLP 2022 paper "RankGen - Improving Text Generation with Large Ranking Models" (https://arx…☆136Updated last year
- The original implementation of Min et al. "Nonparametric Masked Language Modeling" (paper https//arxiv.org/abs/2212.01349)☆157Updated 2 years ago
- ☆97Updated 2 years ago
- Pytorch Implementation of EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks☆63Updated 3 years ago
- ☆24Updated 2 years ago
- ☆72Updated last year
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆75Updated 3 years ago
- ☆35Updated last year
- Repo for "On Learning to Summarize with Large Language Models as References"☆44Updated last year
- The official repository for Efficient Long-Text Understanding Using Short-Text Models (Ivgi et al., 2022) paper☆70Updated last year
- ☆97Updated 2 years ago
- Dense hybrid representations for text retrieval☆62Updated 2 years ago
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.☆93Updated 2 years ago
- ☆65Updated last year
- [AAAI 2024] Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following☆79Updated 7 months ago
- Interpreting Language Models with Contrastive Explanations (EMNLP 2022 Best Paper Honorable Mention)☆62Updated 2 years ago
- Code for the paper Code for the paper InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning☆100Updated last year
- An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation☆27Updated 10 months ago
- Code, datasets, and checkpoints for the paper "Improving Passage Retrieval with Zero-Shot Question Generation (EMNLP 2022)"☆101Updated 2 years ago
- Token-level Reference-free Hallucination Detection☆94Updated last year
- Detect hallucinated tokens for conditional sequence generation.☆64Updated 3 years ago
- [NeurIPS'22 Spotlight] Data and code for our paper CoNT: Contrastive Neural Text Generation☆152Updated last year
- ☆43Updated last year
- ☆21Updated 2 years ago
- Transformers at any scale☆41Updated last year
- Apps built using Inspired Cognition's Critique.☆58Updated 2 years ago
- ☆182Updated last year
- EMNLP 2021 - CTC: A Unified Framework for Evaluating Natural Language Generation☆96Updated 2 years ago
- Code base of In-Context Learning for Dialogue State tracking☆45Updated last year
- Tk-Instruct is a Transformer model that is tuned to solve many NLP tasks by following instructions.☆180Updated 2 years ago