| WebWalker: Benchmarking LLMs in Web Traversal | Jan 13, 2025 | BenchmarkingOpen-Domain Question Answering | CodeCode Available | 11 | 5 |
| What Makes Good In-Context Examples for GPT-3? | Jan 17, 2021 | Few-Shot LearningNatural Language Understanding | CodeCode Available | 4 | 5 |
| Generating Long Sequences with Sparse Transformers | Apr 23, 2019 | DiversityImage Generation | CodeCode Available | 3 | 5 |
| ERNIE 2.0: A Continual Pre-training Framework for Language Understanding | Jul 29, 2019 | Chinese Named Entity RecognitionChinese Reading Comprehension | CodeCode Available | 3 | 5 |
| Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers | Mar 22, 2024 | Information Retrieval | CodeCode Available | 2 | 5 |
| ktrain: A Low-Code Library for Augmented Machine Learning | Apr 19, 2020 | BIG-bench Machine LearningClassification | CodeCode Available | 2 | 5 |
| Reformer: The Efficient Transformer | Jan 13, 2020 | D4RLImage Generation | CodeCode Available | 2 | 5 |
| Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering | Oct 21, 2024 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 2 | 5 |
| Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems | Feb 16, 2025 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 2 | 5 |
| What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams | Sep 28, 2020 | MedQAMultiple-choice | CodeCode Available | 2 | 5 |
| ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning | Feb 11, 2024 | LLM real-life tasksOpen-Domain Question Answering | CodeCode Available | 2 | 5 |
| Relevance-guided Supervision for OpenQA with ColBERT | Jul 1, 2020 | Natural QuestionsOpen-Domain Question Answering | CodeCode Available | 2 | 5 |
| PEDANTS: Cheap but Effective and Interpretable Answer Equivalence | Feb 17, 2024 | BenchmarkingForm | CodeCode Available | 2 | 5 |
| Knowledge Graph Prompting for Multi-Document Question Answering | Aug 22, 2023 | graph constructionOpen-Domain Question Answering | CodeCode Available | 2 | 5 |
| QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs | May 25, 2022 | Answer GenerationNatural Questions | CodeCode Available | 2 | 5 |
| Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation | Oct 11, 2024 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 2 | 5 |
| Learning Dense Representations of Phrases at Scale | Dec 23, 2020 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 2 | 5 |
| RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering | Feb 26, 2024 | FormOpen-Domain Question Answering | CodeCode Available | 2 | 5 |
| A Replication Study of Dense Passage Retriever | Apr 12, 2021 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 2 | 5 |
| TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning | Jun 12, 2025 | Answer GenerationChunking | CodeCode Available | 2 | 5 |
| Can AI Assistants Know What They Don't Know? | Jan 24, 2024 | MathOpen-Domain Question Answering | CodeCode Available | 2 | 5 |
| ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction | Dec 2, 2021 | Information RetrievalOpen-Domain Question Answering | CodeCode Available | 2 | 5 |
| Atlas: Few-shot Learning with Retrieval Augmented Language Models | Aug 5, 2022 | Fact CheckingFew-Shot Learning | CodeCode Available | 2 | 5 |
| Generate rather than Retrieve: Large Language Models are Strong Context Generators | Sep 21, 2022 | Language ModelingLanguage Modelling | CodeCode Available | 2 | 5 |
| RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder | May 24, 2022 | DecoderInformation Retrieval | CodeCode Available | 2 | 5 |
| Learning to Filter Context for Retrieval-Augmented Generation | Nov 14, 2023 | Extractive Question-AnsweringFact Verification | CodeCode Available | 2 | 5 |
| RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models | May 4, 2023 | Information RetrievalOpen-Domain Question Answering | CodeCode Available | 2 | 5 |
| Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering | Sep 20, 2022 | Multimodal Deep LearningMultimodal Reasoning | CodeCode Available | 2 | 5 |
| End-to-End Training of Neural Retrievers for Open-Domain Question Answering | Jan 2, 2021 | Natural QuestionsOpen-Domain Question Answering | CodeCode Available | 1 | 5 |
| Dealing with Typos for BERT-based Passage Retrieval and Ranking | Aug 27, 2021 | Information RetrievalLanguage Modeling | CodeCode Available | 1 | 5 |
| Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding | May 4, 2024 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 1 | 5 |
| CREPE: Open-Domain Question Answering with False Presuppositions | Nov 30, 2022 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 1 | 5 |
| Cross-document Event Coreference Search: Task, Dataset and Modeling | Oct 23, 2022 | Coreference ResolutionCross Document Coreference Resolution | CodeCode Available | 1 | 5 |
| End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering | Jun 9, 2021 | Answer GenerationOpen-Domain Question Answering | CodeCode Available | 1 | 5 |
| EntQA: Entity Linking as Question Answering | Oct 5, 2021 | BenchmarkingEntity Linking | CodeCode Available | 1 | 5 |
| Context Awareness Gate For Retrieval Augmented Generation | Nov 25, 2024 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 1 | 5 |
| Latent Retrieval for Weakly Supervised Open Domain Question Answering | Jun 1, 2019 | Information RetrievalOpen-Domain Question Answering | CodeCode Available | 1 | 5 |
| Contextualized Sparse Representations for Real-Time Open-Domain Question Answering | Nov 7, 2019 | Information RetrievalOpen-Domain Question Answering | CodeCode Available | 1 | 5 |
| ECoRAG: Evidentiality-guided Compression for Long Context RAG | Jun 5, 2025 | Answer GenerationOpen-Domain Question Answering | CodeCode Available | 1 | 5 |
| Adaptive Information Seeking for Open-Domain Question Answering | Sep 14, 2021 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 1 | 5 |
| Conformal Language Modeling | Jun 16, 2023 | Conformal PredictionLanguage Modeling | CodeCode Available | 1 | 5 |
| Efficient Passage Retrieval with Hashing for Open-domain Question Answering | Jun 2, 2021 | Natural QuestionsOpen-Domain Question Answering | CodeCode Available | 1 | 5 |
| ELI5: Long Form Question Answering | Jul 22, 2019 | FormLanguage Modeling | CodeCode Available | 1 | 5 |
| CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training | Oct 14, 2021 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 1 | 5 |
| Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions? | Feb 23, 2023 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 1 | 5 |
| Chain-of-Skills: A Configurable Model for Open-domain Question Answering | May 4, 2023 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 1 | 5 |
| CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management | May 4, 2020 | ArticlesDocument Summarization | CodeCode Available | 1 | 5 |
| BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression | Oct 20, 2024 | In-Context LearningLong-Context Understanding | CodeCode Available | 1 | 5 |
| Compositional Exemplars for In-context Learning | Feb 11, 2023 | Code GenerationContrastive Learning | CodeCode Available | 1 | 5 |
| Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation | Oct 10, 2021 | Open-Domain Question AnsweringQuestion Answering | CodeCode Available | 1 | 5 |
