mlsanityData to 14 Oct 2026

How Well Do Large Language Models Truly Ground?

arXiv 2311.09069 ↗First posted 15 Nov 2023cs.CL cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

To reduce issues like hallucinations and lack of control in Large Language Models (LLMs), a common method is to generate responses by grounding on external contexts given as input, known as knowledge-augmented models. However, previous research often narrowly defines "grounding" as just having the correct answer, which does not ensure the reliability of the entire response. To overcome this, we propose a stricter definition of grounding: a model is truly grounded if it (1) fully utilizes the necessary knowledge from the provided context, and (2) stays within the limits of that knowledge. We introduce a new dataset and a grounding metric to evaluate model capability under the definition. We perform experiments across 25 LLMs of different sizes and training methods and provide insights into factors that influence grounding performance. Our findings contribute to a better understanding of how to improve grounding capabilities and suggest an area of improvement toward more reliable and controllable LLM applications.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 40 of its 67 references that are in the map. First posted on arXiv 15 Nov 2023.

Builds on

40 of 67 references.

References · 40

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  8. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  9. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  10. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  11. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  12. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
28 more
  1. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  2. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  3. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  4. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  5. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  6. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  7. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  8. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 763
  9. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  10. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  11. 2023Zephyr: Direct Distillation of LM Alignmentcited by 506
  12. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  13. 2023How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resourcescited by 408
  14. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  15. 2021TransVG: End-to-End Visual Grounding with Transformerscited by 271
  16. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 248
  17. 2023Poisoning Retrieval Corpora by Injecting Adversarial Passagescited by 159
  18. 2022Rethinking with Retrieval: Faithful Large Language Model Inferencecited by 145
  19. 2022Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluationcited by 142
  20. 2021How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVENcited by 124
  21. 2023WiCE: Real-World Entailment for Claims in Wikipediacited by 120
  22. 2022Grounding Language with Visual Affordances over Unstructured Datacited by 101
  23. 2023Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generationcited by 96
  24. 2021Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?cited by 62
  25. 2022Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Modelcited by 32
  26. 2022Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Groundingcited by 22
  27. 2022Black-box language model explanation by context length probingcited by 7
  28. 2023KGConv, a Conversational Corpus grounded in Wikidatacited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 5; 2026: 4.

14 papers.

Sort:

By area:

  1. 2024Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbationscited by 65
  2. 2024MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Modelscited by 35
  3. 2024On Mitigating Code LLM Hallucinations with API Documentationcited by 21
  4. 2025Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Modelscited by 7
  5. 2025"Lost-in-the-Later": Framework for Quantifying Contextual Grounding in Large Language Modelscited by 5
  6. 2025Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modelingcited by 5
  7. 2026Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streamscited by 5
  8. 2025CORG: Generating Answers from Complex, Interrelated Contextscited by 3
  9. 2026MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environmentscited by 3
  10. 2026Multimodal Fact-Level Attribution for Verifiable Reasoningcited by 2
  11. 2024Semiparametric Token-Sequence Co-Supervisioncited by 1
  12. 2025InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Groundingcited by 1
2 more
  1. 2024DSAI: Unbiased and Interpretable Latent Feature Extraction for Data-Centric AIcited by 0
  2. 2026Talking to Your Data: Exploring Embodied Conversation as an Interface for Personal Health Reflectioncited by 0