# Retrieving Supporting Evidence for Generative Question Answering

arXiv: https://arxiv.org/abs/2309.11392 · HTML: https://mlsanity.com/paper/2309.11392/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2023.

## Built on by (most cited first, 30 of 31)

- [The Effect of Sampling Temperature on Problem Solving in Large Language Models](https://mlsanity.com/paper/2402.05201/) (2024)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [Large Language Models Hallucination: A Comprehensive Survey](https://mlsanity.com/paper/2510.06265/) (2025)
- [RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects](https://mlsanity.com/paper/2501.18365/) (2025)
- [Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering](https://mlsanity.com/paper/2405.17980/) (2024)
- [Are Large Language Models Reliable Argument Quality Annotators?](https://mlsanity.com/paper/2404.09696/) (2024)
- [AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution](https://mlsanity.com/paper/2411.15102/) (2024)
- [Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs](https://mlsanity.com/paper/2411.19187/) (2024)
- [ALiiCE: Evaluating Positional Fine-grained Citation Generation](https://mlsanity.com/paper/2406.13375/) (2024)
- [TokenShapley: Token Level Context Attribution with Shapley Value](https://mlsanity.com/paper/2507.05261/) (2025)
- [Retrieval-Enhanced Machine Learning: Synthesis and Opportunities](https://mlsanity.com/paper/2407.12982/) (2024)
- [MedCite: Can Language Models Generate Verifiable Text for Medicine?](https://mlsanity.com/paper/2506.06605/) (2025)
- [LLM4DSR: Leveraging Large Language Model for Denoising Sequential Recommendation](https://mlsanity.com/paper/2408.08208/) (2024)
- [WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations](https://mlsanity.com/paper/2403.01774/) (2024)
- [Harnessing Business and Media Insights with Large Language Models](https://mlsanity.com/paper/2406.06559/) (2024)
- [Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents](https://mlsanity.com/paper/2506.01344/) (2025)
- [ChartLens: Fine-grained Visual Attribution in Charts](https://mlsanity.com/paper/2505.19360/) (2025)
- [Addressing Hallucinations in Language Models with Knowledge Graph Embeddings as an Additional Modality](https://mlsanity.com/paper/2411.11531/) (2024)
- [Long-context Non-factoid Question Answering in Indic Languages](https://mlsanity.com/paper/2504.13615/) (2025)
- [SafePassage: High-Fidelity Information Extraction with Black Box LLMs](https://mlsanity.com/paper/2510.00276/) (2025)
- [RAG over Thinking Traces Can Improve Reasoning Tasks](https://mlsanity.com/paper/2605.03344/) (2026)
- [LLM Assistance for Pediatric Depression](https://mlsanity.com/paper/2501.17510/) (2025)
- [Retrieval Augmented Generation-based Large Language Models for Bridging Transportation Cybersecurity Legal Knowledge Gaps](https://mlsanity.com/paper/2505.18426/) (2025)
- [VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answering](https://mlsanity.com/paper/2604.08549/) (2026)
- [SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking](https://mlsanity.com/paper/2503.00955/) (2025)
- [Unraveling Media Perspectives: A Comprehensive Methodology Combining Large Language Models, Topic Modeling, Sentiment Analysis, and Ontology Learning to Analyse Media Bias](https://mlsanity.com/paper/2505.01754/) (2025)
- [Agent-Based Detection and Resolution of Incompleteness and Ambiguity in Interactions with Large Language Models](https://mlsanity.com/paper/2507.03726/) (2025)
- [Noise or Nuance: An Investigation Into Useful Information and Filtering For LLM Driven AKBC](https://mlsanity.com/paper/2509.08903/) (2025)
- [Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Survey](https://mlsanity.com/paper/2601.19927/) (2026)

## Abstract (arXiv)

Current large language models (LLMs) can exhibit near-human levels of performance on many natural language-based tasks, including open-domain question answering. Unfortunately, at this time, they also convincingly hallucinate incorrect answers, so that responses to questions must be verified against external sources before they can be accepted at face value. In this paper, we report two simple experiments to automatically validate generated answers against a corpus. We base our experiments on questions and passages from the MS MARCO (V1) test collection, and a retrieval pipeline consisting of sparse retrieval, dense retrieval and neural rerankers. In the first experiment, we validate the generated answer in its entirety. After presenting a question to an LLM and receiving a generated answer, we query the corpus with the combination of the question + generated answer. We then present the LLM with the combination of the question + generated answer + retrieved answer, prompting it to indicate if the generated answer can be supported by the retrieved answer. In the second experiment, we consider the generated answer at a more granular level, prompting the LLM to extract a list of factual statements from the answer and verifying each statement separately. We query the corpus with each factual statement and then present the LLM with the statement and the corresponding retrieved evidence. The LLM is prompted to indicate if the statement can be supported and make necessary edits using the retrieved material. With an accuracy of over 80%, we find that an LLM is capable of verifying its generated answer when a corpus of supporting material is provided. However, manual assessment of a random sample of questions reveals that incorrect generated answers are missed by this verification process. While this verification process can reduce hallucinations, it can not entirely eliminate them.