BPM Team of Tsinghua University

MarkLLM

MarkLLM: An Open-Source Toolkit for LLM Watermarking.

chatgpt-sql

The prediction results of ChatGPT on various datasets of Text-to-SQL.

CHEF

The source code of paper "CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking"

PairSCL

The source code of paper "PAIR-LEVEL SUPERVISED CONTRASTIVE LEARNING FOR NATURAL LANGUAGE INFERENCE" at ICASSP 2022.

SelfORE

The source code of paper "SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction"

MR2

GradLRE

The source code of paper "Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction"

Robust_Watermark

Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.

unforgeable_watermark

Source code of paper "An Unforgeable Publicly Verifiable Watermark for Large Language Models" accepted by ICLR 2024

MetaSRE

The source code of paper "Semi-supervised Relation Extraction via Incremental Meta Self-Training"

HiURE

The source code of paper "HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction" in NAACL 2022

ISESL-SQL

The source code of paper "Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graph" in KDD2022.

RAPL

Code and data for EMNLP 2023 paper "RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction"

APARN

Code and datasets of our paper "AMR-based Network for Aspect-based Sentiment Analysis" accepted by ACL 2023.

PROMU

Source code of paper:"Prompt Me Up: Unleashing the Power of Alignments for Multimodal Entity and Relation Extraction".

CWBA

The source code of paper "Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution" at EMNLP 2022.

Pinocchio

Dataset Pinocchio for paper "Towards Understanding Factual Knowledge of Large Language Models" accepted by ICLR 2024 (Spotlight)

RE2

The source code of paper "Think Rationally about What You See: Continuous Rationale Extraction for Relation Extraction" at SIGIR 2023.

ReRead

The source code of paper "Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence" at SIGIR 2023.

SGM

The source code of paper "Scene Graph Modification as Incremental Structure Expanding"

CD-Text2SQL-CG

MultiSCL

The source code of paper "A Multi-level Supervised Contrastive Learning Framework for Low-Resource Natural Language Inference" at TASLP.

CoEP

The implementation of CoEP model.

Env-DocRE

Code and data for ACL 2024 Findings paper "On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations"

LLMArena

Code for paper "LLMARENA: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments" accepted by ACL 2024

SelfLRE

SoftMV

The source code of paper "Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer" at ACL 2023.

FSMR

The source code of paper "A Feature Swapping Multi-modal Reasoning Framework for PMR""