Tongyi Lab, Alibaba Group ORG

Tongyi Deep Research, the Leading Open-source Deep Research Agent

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Multimodal Retrieval-augmented Generation Framework Built by Tongyi Lab, Alibaba Group.

[EMNLP 2025] ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents

Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

[ACL-IJCNLP 2021] Automated Concatenation of Embeddings for Structured Prediction

Repo for NAACL 2025 Paper "Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization"

An Instruction-tuned Large Language Model for E-commerce

qqr is an RL training framework for open-ended agents.

Hierarchy-Aware Global Model for Hierarchical Text Classification

SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding

[SIGIR 2022] Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval

Winner system (DAMO-NLP) of SemEval 2022 MultiCoNER shared task over 10 out of 13 tracks.

Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"

[ACL-IJCNLP 2021] Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

[ACL 2020] Structure-Level Knowledge Distillation For Multilingual Sequence Labeling

E2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker

The code for LaRA Benchmark

No description.

code for paper 《RankingGPT: Empowering Large Language Models in Text Ranking with Progressive Enhancement》

[EMNLP 2021] MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations

Code for 'Prototypical Representation Learning for Relation Extraction'.

[ICASSP 2022] AISHELL-NER: Named Entity Recognition from Chinese Speech

Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation

[ACL 2023] MANNER: A Variational Memory-Augmented Model for Cross Domain Few-Shot Named Entity Recognition

Hybrid List Aware Transformer Reranking

Code for our EMNLP 2020 Paper "AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network"

CDQA: Chinese Dynamic Question Answering Benchmark

Codes for the EMNLP'2020 paper "Predicting Clinical Trial Results by Implicit Evidence Integration".

[ACL-IJCNLP 2021] Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor

A new evaluation paradigm for deep search that identifies specific LLM failure sources, introduces challenging hint-free datasets with holistic evaluation, and offers a strong baseline incorporating memory and verification.

Source code of paper Improving "Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts

This is the official repository for the IBKD knowledge distillation method, as described in the paper .

No description.

[EMNLP 2025] Code for "Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference"

No description.

Implementation of NeurIPS 20 paper: Latent Template Induction with Gumbel-CRFs

Implementation of AAAI 21 paper: Nested Named Entity Recognition with Partially Observed TreeCRFs

No description.

[ACL 2022 Findings] Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition

[ACL 2022] Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding

Codes and data for Alibaba's winning systems at the TREC Precision Medicine Track 2020.

Implementation of ICLR 21 paper: Probing BERT in Hyperbolic Spaces