The lastest paper about detection of LLM-generated text and code

This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.

Offiical codes for DNA-GPT (ICLR 2024)

Codes for ACL 2023 Paper "Fact-Checking Complex Claims with Program-Guided Reasoning"

The project page for "LOGIC-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning"

LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation

Multimodal-Procedural-Planning

Conversation Branches and DAGs. Pytorch. The data and code of paper "CausalDialogue: Modeling Utterance-level Causality in Conversations" ACL-Findings 2023.

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

WikiWhy is a new benchmark for evaluating LLMs' ability to explain between cause-effect relationships. It is a QA dataset containing 9000+ "why" question-answer-rationale triplets.

Few-shot Learning with Auxiliary Data

Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

Implementation of "Visualize Before You Write: Imagination-Guided Open-Ended Text Generation".

Data and code for EMNLP 2022 paper "ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering"

Official repo for "Imagination-Augmented Natural Language Understanding", NAACL 2022.

KETOD Knowledge-Enriched Task-Oriented Dialogue

NLP Information-grounded dialogue over heterogeneous information

Code and data for EMNLP 2021 paper "A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space."

Code for "Diagnosing Vision-and-language Navigation: What Really Matters"

A unified approach to explain conditional text generation models. Pytorch. The code of paper "Local Explanation of Dialogue Response Generation, NeurIPS 2021"

This is the repository for the paper: Counterfactual Maximum Likelihood Estimation for Training Deep Networks.

Starter Code for VALUE benchmark

Code and Data for NeurIPS2021 Paper "A Dataset for Answering Time-Sensitive Questions"

Data and code for EMNLP 2021 paper "FinQA: A Dataset of Numerical Reasoning over Financial Data"

Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"

An implementation of SSI