ShaojieJiang / CT-LossLinks
The contrastive token loss function for reducing generative repetition of autoregressive neural language models.
☆13Updated 3 years ago
Alternatives and similar repositories for CT-Loss
Users that are interested in CT-Loss are comparing it to the libraries listed below
Sorting:
- The code implementation of the EMNLP2022 paper: DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Gene…☆27Updated 2 years ago
- ☆50Updated 2 years ago
- TBC☆27Updated 3 years ago
- Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking☆13Updated 2 years ago
- ☆17Updated 2 years ago
- We construct and introduce DIALFACT, a testing benchmark dataset crowd-annotated conversational claims, paired with pieces of evidence fr…☆44Updated 3 years ago
- ☆58Updated 3 years ago
- The implementation of <Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation> in PyTorch.☆17Updated 4 years ago
- Detect hallucinated tokens for conditional sequence generation.☆64Updated 3 years ago
- The official implemetation of "Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks" (NAACL 2022).☆45Updated 2 years ago
- Code for the ACL2022 paper "Synthetic Question Value Estimation for Domain Adaptation of Question Answering"☆17Updated 3 years ago
- First explanation metric (diagnostic report) for text generation evaluation☆62Updated 8 months ago
- [NAACL 2022] Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning.☆57Updated last year
- Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors (ACL 2023)☆27Updated last year
- ☆16Updated 3 years ago
- Token-level Reference-free Hallucination Detection☆96Updated 2 years ago
- Code for EMNLP 2021 paper: Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting☆17Updated 3 years ago
- [NAACL 2022] Contrastive Learning for Prompt-based Few-shot Language Learners☆22Updated 2 years ago
- [EMNLP 2022] Code and data for "Controllable Dialogue Simulation with In-Context Learning"☆35Updated 2 years ago
- The implementation of the paper "Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters".☆17Updated 3 years ago
- code for the table-based open domain question answering project, with paper title: "Reasoning over Hybrid Chain for Table-and-Text Open D…☆12Updated 3 years ago
- Code base of In-Context Learning for Dialogue State tracking☆45Updated 2 years ago
- Findings of ACL'2023: Optimizing Test-Time Query Representations for Dense Retrieval☆30Updated 2 years ago
- PyTorch code for "FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization" (NAACL 2022)☆40Updated 3 years ago
- The official implementation for ACL 2021 "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval".☆28Updated 4 years ago
- Mutual Information Predicts Hallucinations in Abstractive Summarization☆13Updated 3 years ago
- This repository contains the code for paper Prompting ELECTRA Few-Shot Learning with Discriminative Pre-Trained Models.☆48Updated 3 years ago
- Code for Editing Factual Knowledge in Language Models☆142Updated 3 years ago
- Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Textual Style Transfer☆36Updated 3 years ago
- The project page for "SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables"☆23Updated last year