mlsanityData to 7 Oct 2026

Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks

arXiv 2112.08688 ↗First posted 16 Dec 2021cs.CLcited by 40

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-augmented generation models have shown state-of-the-art performance across many knowledge-intensive NLP tasks such as open question answering and fact verification. These models are trained to generate the final output given the retrieved passages, which can be irrelevant to the original query, leading to learning spurious cues or answer memorization. This work introduces a method to incorporate the evidentiality of passages -- whether a passage contains correct evidence to support the output -- into training the generator. We introduce a multi-task learning framework to jointly generate the final output and predict the evidentiality of each passage, leveraging a new task-agnostic method to obtain silver evidentiality labels for supervision. Our experiments on five datasets across three knowledge-intensive tasks show that our new evidentiality-guided generator significantly outperforms its direct counterpart with the same-size model and advances the state of the art on FaVIQ-Ambig. We attribute these improvements to both the auxiliary multi-task learning and silver evidentiality mining techniques.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 39 of its 67 references that are in the map. First posted on arXiv 16 Dec 2021.

Builds on

39 of 67 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  7. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  8. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  9. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  10. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  11. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  12. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
27 more
  1. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  2. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  3. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  4. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  5. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  6. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  7. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 349
  8. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  9. 2021Hurdles to Progress in Long-form Question Answeringcited by 166
  10. 2020Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasetscited by 137
  11. 2019A Question-Entailment Approach to Question Answeringcited by 133
  12. 2017Simple and Effective Multi-Paragraph Reading Comprehensioncited by 120
  13. 2020Unsupervised Question Decomposition for Question Answeringcited by 118
  14. 2019A Discrete Hard EM Approach for Weakly Supervised Question Answeringcited by 78
  15. 2019Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answeringcited by 58
  16. 2021Can NLI Models Verify QA Systems' Predictions?cited by 46
  17. 2020Challenges in Information-Seeking QA: Unanswerable Questions and Paragraph Retrievalcited by 44
  18. 2021Multi-task Retrieval for Knowledge-Intensive Taskscited by 44
  19. 2019Multi-hop Question Answering via Reasoning Chainscited by 42
  20. 2019Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extractioncited by 39
  21. 2021Hindsight: Posterior-guided training of retrievers for improved open-ended generationcited by 38
  22. 2021R2-D2: A Modular Baseline for Open-Domain Question Answeringcited by 37
  23. 2021FaVIQ: FAct Verification from Information-seeking Questionscited by 36
  24. 2021Robust Retrieval Augmented Generation for Zero-shot Slot Fillingcited by 24
  25. 2021Attention-guided Generative Models for Extractive Question Answeringcited by 14
  26. 2021Robustifying Multi-hop QA through Pseudo-Evidentiality Trainingcited by 13
  27. 2019Repurposing Entailment for Multi-Hop Question Answering Taskscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 12; 2024: 10; 2025: 7; 2026: 4.

40 papers.

Sort:

By area:

  1. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  2. 2023Evaluating Open-Domain Question Answering in the Era of Large Language Modelscited by 110
  3. 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 82
  4. 2022FiD-Light: Efficient and Effective Retrieval-Augmented Text Generationcited by 63
  5. 2023NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notescited by 48
  6. 2023Merging Generated and Retrieved Knowledge for Open-Domain QAcited by 36
  7. 2024Grounding Language Model with Chunking-Free In-Context Retrievalcited by 30
  8. 2024Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systemscited by 27
  9. 2024An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generationcited by 16
  10. 2023Why LLMs Hallucinate, and How to Get (Evidential) Closure: Perceptual, Intensional, and Extensional Learning for Faithful Natural Language Generationcited by 13
  11. 2022Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Predictioncited by 12
  12. 2022MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languagescited by 11
28 more
  1. 2023Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generationcited by 11
  2. 2024SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsingcited by 11
  3. 2024Retrieval-Enhanced Machine Learning: Synthesis and Opportunitiescited by 11
  4. 2022Multi-Task Retrieval-Augmented Text Generation with Relevance Samplingcited by 10
  5. 2024RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generationcited by 10
  6. 2025Controlled Retrieval-augmented Context Evaluation for Long-form RAGcited by 9
  7. 2023Expository Text Generation: Imitate, Retrieve, Paraphrasecited by 8
  8. 2025EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notescited by 8
  9. 2022Knowledge Transfer from Answer Ranking to Answer Generationcited by 6
  10. 2022Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Modelscited by 6
  11. 2026SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answeringcited by 6
  12. 2023RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answeringcited by 4
  13. 2025ECoRAG: Evidentiality-guided Compression for Long Context RAGcited by 4
  14. 2026When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMscited by 4
  15. 2023Learning Answer Generation using Supervision from Automatic Question Answering Evaluatorscited by 3
  16. 2023Retrieval-Based Transformer for Table Augmentationcited by 3
  17. 2024How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Modelscited by 3
  18. 2023Reimagining Retrieval Augmented Language Models for Answering Queriescited by 2
  19. 2024Multi-Granularity Guided Fusion-in-Decodercited by 2
  20. 2025Gumbel Reranking: Differentiable End-to-End Reranker Optimizationcited by 2
  21. 2024Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generationcited by 1
  22. 2025Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generationcited by 1
  23. 2025ACoRN: Noise-Robust Abstractive Compression in Retrieval-Augmented Language Modelscited by 1
  24. 2023Detrimental Contexts in Open-Domain Question Answeringcited by 0
  25. 2024E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generationcited by 0
  26. 2025Noise-Robust Abstractive Compression in Retrieval-Augmented Language Modelscited by 0
  27. 2026Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoningcited by 0
  28. 2026Warranted Attention: Learning What to Pass from Attention to Predictioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG
  2. 2025NeoQA: Evidence-based Question Answering with Generated News Events
  3. 2026EvidentialRAG: Quantifying and Mitigating Information Conflict in Multi-Source Retrieval-Augmented Generation via Evidential Deep Learning
  4. 2025GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs
  5. 2026ERA: Evidence-based Reliability Alignment for Honest Retrieval-Augmented Generation
  6. 2026Coordinated Semantic Alignment and Evidence Constraints for Retrieval-Augmented Generation with Large Language Models
  7. 2026SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation
  8. 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation