| LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding | Apr 25, 2024 | GSM8KHellaSwag | CodeCode Available | 3 | 5 |
| ST-MoE: Designing Stable and Transferable Sparse Expert Models | Feb 17, 2022 | ARCCommon Sense Reasoning | CodeCode Available | 3 | 5 |
| GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning | May 30, 2024 | Graph Question AnsweringKnowledge Graphs | CodeCode Available | 3 | 5 |
| Atlas: Few-shot Learning with Retrieval Augmented Language Models | Aug 5, 2022 | Fact CheckingFew-Shot Learning | CodeCode Available | 2 | 5 |
| Scaling Language Models: Methods, Analysis & Insights from Training Gopher | Dec 8, 2021 | Abstract AlgebraAnachronisms | CodeCode Available | 2 | 5 |
| Relevance-guided Supervision for OpenQA with ColBERT | Jul 1, 2020 | Natural QuestionsOpen-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 |
| DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving | Jun 18, 2024 | Arithmetic ReasoningMath | CodeCode Available | 2 | 5 |
| JADE: A Linguistics-based Safety Evaluation Platform for Large Language Models | Nov 1, 2023 | Natural Questions | CodeCode Available | 2 | 5 |
| Text and Code Embeddings by Contrastive Pre-Training | Jan 24, 2022 | Code SearchLinear-Probe Classification | CodeCode Available | 1 | 5 |
| MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering | Jul 30, 2020 | Extractive Question-AnsweringNatural Questions | CodeCode Available | 1 | 5 |
| MultiSpanQA: A Dataset for Multi-Span Question Answering | Jul 1, 2022 | Natural QuestionsQuestion Answering | CodeCode Available | 1 | 5 |
| TempoQR: Temporal Question Reasoning over Knowledge Graphs | Dec 10, 2021 | Entity EmbeddingsGraph Question Answering | CodeCode Available | 1 | 5 |
| Generative Retrieval via Term Set Generation | May 23, 2023 | Information RetrievalNatural Questions | CodeCode Available | 1 | 5 |
| Table Retrieval May Not Necessitate Table-specific Model Design | May 19, 2022 | Hard AttentionNatural Questions | CodeCode Available | 1 | 5 |
| Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering | May 25, 2022 | Graph Question AnsweringNatural Questions | CodeCode Available | 1 | 5 |
| Recitation-Augmented Language Models | Oct 4, 2022 | Natural QuestionsQuestion Answering | CodeCode Available | 1 | 5 |
| DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering | Nov 10, 2022 | counterfactualData Augmentation | CodeCode Available | 1 | 5 |
| Generation-Augmented Retrieval for Open-domain Question Answering | Sep 17, 2020 | Natural QuestionsOpen-Domain Question Answering | CodeCode Available | 1 | 5 |
| How Do We Answer Complex Questions: Discourse Structure of Long-form Answers | Mar 21, 2022 | FormNatural Questions | CodeCode Available | 1 | 5 |
| RealFormer: Transformer Likes Residual Attention | Dec 21, 2020 | Language ModelingLanguage Modelling | CodeCode Available | 1 | 5 |
| Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering | Jan 1, 2021 | Natural QuestionsOpen-Domain Question Answering | CodeCode Available | 1 | 5 |
| Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval | Apr 7, 2025 | Information RetrievalNatural Questions | CodeCode Available | 1 | 5 |
| Model-enhanced Vector Index | Sep 23, 2023 | modelNatural Questions | CodeCode Available | 1 | 5 |
| RECONSIDER: Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answering | Oct 21, 2020 | Machine Reading ComprehensionNatural Questions | CodeCode Available | 1 | 5 |
| CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems | Apr 2, 2024 | FormLong Form Question Answering | CodeCode Available | 1 | 5 |
| Asyncval: A Toolkit for Asynchronously Validating Dense Retriever Checkpoints during Training | Feb 25, 2022 | GPUNatural Questions | CodeCode Available | 1 | 5 |
| Multi-Granularity Guided Fusion-in-Decoder | Apr 3, 2024 | DecoderMulti-Task Learning | CodeCode Available | 1 | 5 |
| Constructing and Evaluating Declarative RAG Pipelines in PyTerrier | Jun 12, 2025 | Natural QuestionsRAG | CodeCode Available | 1 | 5 |
| Continual Learning with Knowledge Transfer for Sentiment Classification | Dec 18, 2021 | ClassificationContinual Learning | CodeCode Available | 1 | 5 |
| On the Effectiveness of Parameter-Efficient Fine-Tuning | Nov 28, 2022 | Natural Questionsparameter-efficient fine-tuning | CodeCode Available | 1 | 5 |
| Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval | Apr 18, 2021 | BIG-bench Machine LearningDomain Adaptation | CodeCode Available | 1 | 5 |
| FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection | Aug 12, 2024 | Answer GenerationDecoder | CodeCode Available | 1 | 5 |
| Open Domain Question Answering with A Unified Knowledge Interface | Oct 16, 2021 | Data-to-Text GenerationNatural Questions | 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 |
| End-to-End Training of Neural Retrievers for Open-Domain Question Answering | Jan 2, 2021 | Natural QuestionsOpen-Domain Question Answering | CodeCode Available | 1 | 5 |
| C3VQG: Category Consistent Cyclic Visual Question Generation | May 15, 2020 | Natural QuestionsQuestion Generation | CodeCode Available | 1 | 5 |
| Exploiting Abstract Meaning Representation for Open-Domain Question Answering | May 26, 2023 | Abstract Meaning RepresentationDiversity | CodeCode Available | 1 | 5 |
| AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data | Oct 9, 2020 | AttributeNatural Questions | CodeCode Available | 1 | 5 |
| Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence | May 27, 2021 | ArticlesDocument Ranking | CodeCode Available | 1 | 5 |
| Event Extraction by Answering (Almost) Natural Questions | Apr 28, 2020 | Event Argument ExtractionEvent Extraction | CodeCode Available | 1 | 5 |
| Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering | Jul 2, 2020 | Natural QuestionsOpen-Domain Question Answering | CodeCode Available | 1 | 5 |
| Poisoning Retrieval Corpora by Injecting Adversarial Passages | Oct 29, 2023 | Information RetrievalNatural Questions | CodeCode Available | 1 | 5 |
| Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension | May 12, 2020 | Graph AttentionMachine Reading Comprehension | CodeCode Available | 1 | 5 |
| Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering | Nov 10, 2019 | Natural QuestionsOpen-Domain Question Answering | CodeCode Available | 1 | 5 |
| QED: A Framework and Dataset for Explanations in Question Answering | Sep 8, 2020 | Explanation GenerationNatural Questions | CodeCode Available | 1 | 5 |
| Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness | Jan 21, 2023 | DiagnosticNatural Questions | CodeCode Available | 1 | 5 |
| AdANNS: A Framework for Adaptive Semantic Search | May 30, 2023 | Natural QuestionsQuantization | CodeCode Available | 1 | 5 |
| LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors | Jun 20, 2024 | 16kInstruction Following | CodeCode Available | 1 | 5 |
| Summarization-Based Document IDs for Generative Retrieval with Language Models | Nov 14, 2023 | ArticlesLanguage Modeling | CodeCode Available | 0 | 5 |
