yhshu

dpr-scale

Scalable training for dense retrieval models.

ReContriever

Implementation for ACL 2023 Findings paper "Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training"

MuVER

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

2wikimultihop

beir

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

ai2thor

An open-source platform for Visual AI.

intercode

[NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898

ContextualSP

Multiple paper open-source codes of the Microsoft Research Asia DKI group

LongBench

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Awesome-Knowledge-Graph-Reasoning

AKGR: Awesome Knowledge Graph Reasoning is a collection of knowledge graph reasoning works, including papers, codes and datasets

awesome-language-agents

List of language agents based on paper "Cognitive Architectures for Language Agents"

miniwob-plusplus

MiniWoB++: a web interaction benchmark for reinforcement learning

llm-dataset-chinese-poetry

目标：整理一份高质量的大模型古诗词数据集，涵盖先秦到现代

ash-prompting

"Hierarchical Prompting Assists Large Language Model on Web Navigation", EMNLP Findings 2023; NLRSE workshop @ ACL 2023

hagrid

A Human-LLM Collaborative Dataset for Generative Information-seeking with Attribution

webarena

Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

Mind2Web

[NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web"

Lemur

[ICLR 2024] Lemur: Open Foundation Models for Language Agents

dolma

Data and tools for generating and inspecting OLMo pre-training data.

AgentBench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

gStore

gStore - a graph based RDF triple store.

qlever

Very fast SPARQL Engine, which can handle very large knowledge graphs like the complete Wikidata, offers context-sensitive autocompletion for SPARQL queries, and allows combination with text search. It's faster than engines like Blazegraph or Virtuoso, especially for queries involving large result sets.

OpenAgents

OpenAgents: An Open Platform for Language Agents in the Wild

msgraph-sdk-python

KB-BINDER

Few-shot In-context Learning for Knowledge Base Question Answering

Baichuan-13B

A 13B large language model developed by Baichuan Intelligent Technology

alphadev

QDTQA

Code for AAAI 2023 research track paper "Question Decomposition Tree for Answering Complex Questions over Knowledge Bases"

decode-answer-logical-form

tango

Organize your experiments into discrete steps that can be cached and reused throughout the lifetime of your research project.