Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)

Rerank Before You Reason (ACL 2026 Findings): reranking + Effective Token Cost analysis for deep-search agents on BrowseComp-Plus.

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

A high-throughput and memory-efficient inference and serving engine for LLMs

Fast search index for SPLADE sparse retrieval models implemented in Python using Numpy and Numba

EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline (COLM '25)

A Benchmark for Reasoning-Driven Retrieval in Medicine

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent (ACL 2026 Main)

Official repository for paper "ReasonIR Training Retrievers for Reasoning Tasks".

Complex Reasoning Rag System, Agentic Rag System

Test-time compute in information retrieval

Synthetically Generating Intent-Aware Information-Seeking Dialogues! Useful for various tasks such as training/evaluating User Intent Predictors with the possibility to training/evaluating on real …

[ICLR 2025] BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

Evaluating tool-augmented LLMs in conversation settings

The implementation for CIKM 2024: Towards Completeness-Oriented Tool Retrieval for Large Language Models.

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

Research on Learned Sparse Retrieval Derived from Transformers-based Ranking for Information Retrieval

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

[Official Codes] Synthetic Test Collections for Retrieval Evaluation (SIGIR 2024)

Codes and packages for the paper titled Evaluating Retrieval Quality in Retrieval-Augmented Generation.

[SIGIR 2024] The official repo for paper "Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decoding"

Source Code for "Incorporating Retrieval Information into the Truncation of Ranking Lists for Better Legal Search", SIGIR22

This is the official code for the EMNLP 2023 paper "GLEN: Generative Retrieval via Lexical Index Learning".

[WWW 2024] The official repo for paper "Scalable and Effective Generative Information Retrieval".

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Aspect Based ReDial(AB-ReDial): Is a subset data from ReDial annotated on six dialogue aspects and overall user satisfaction at the turn and dialogue levels with the following aspects; relevance, i…

Document Ranking with Large Language Models.