# Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering

arXiv: https://arxiv.org/abs/2405.17980 · HTML: https://mlsanity.com/paper/2405.17980/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 28 May 2024.

## Builds on (most cited first, 26 of 26)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [Truthful AI: Developing and governing AI that does not lie](https://mlsanity.com/paper/2110.06674/) (2021)
- [The Fact Extraction and VERification (FEVER) Shared Task](https://mlsanity.com/paper/1811.10971/) (2018)
- [Retrieving Multimodal Information for Augmented Generation: A Survey](https://mlsanity.com/paper/2303.10868/) (2023)
- [Inseq: An Interpretability Toolkit for Sequence Generation Models](https://mlsanity.com/paper/2302.13942/) (2023)
- [Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark](https://mlsanity.com/paper/2105.00071/) (2021)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution](https://mlsanity.com/paper/2307.16883/) (2023)
- [Towards better understanding of gradient-based attribution methods for Deep Neural Networks](https://mlsanity.com/paper/1711.06104/) (2017)
- ["According to ...": Prompting Language Models Improves Quoting from Pre-Training Data](https://mlsanity.com/paper/2305.13252/) (2023)
- [A Survey on Truth Discovery](https://mlsanity.com/paper/1505.02463/) (2015)
- [Retrieving Supporting Evidence for Generative Question Answering](https://mlsanity.com/paper/2309.11392/) (2023)
- [SEMQA: Semi-Extractive Multi-Source Question Answering](https://mlsanity.com/paper/2311.04886/) (2023)

## Built on by (most cited first, 25 of 25)

- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.13663/) (2024)
- [Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs](https://mlsanity.com/paper/2411.19187/) (2024)
- [SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models](https://mlsanity.com/paper/2502.09604/) (2025)
- [PLD+: Accelerating LLM inference by leveraging Language Model Artifacts](https://mlsanity.com/paper/2412.01447/) (2024)
- [TokenShapley: Token Level Context Attribution with Shapley Value](https://mlsanity.com/paper/2507.05261/) (2025)
- [Learning to Attribute with Attention](https://mlsanity.com/paper/2504.13752/) (2025)
- [LAQuer: Localized Attribution Queries in Content-grounded Generation](https://mlsanity.com/paper/2506.01187/) (2025)
- [Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition](https://mlsanity.com/paper/2409.17073/) (2024)
- [Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models](https://mlsanity.com/paper/2508.15396/) (2025)
- [Generation-Time vs. Post-hoc Citation: A Holistic Evaluation of LLM Attribution](https://mlsanity.com/paper/2509.21557/) (2025)
- [Attention with Dependency Parsing Augmentation for Fine-Grained Attribution](https://mlsanity.com/paper/2412.11404/) (2024)
- [GenerationPrograms: Fine-grained Attribution with Executable Programs](https://mlsanity.com/paper/2506.14580/) (2025)
- [Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Dataset](https://mlsanity.com/paper/2603.23607/) (2026)
- [Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents](https://mlsanity.com/paper/2507.14819/) (2025)
- [On Synthesizing Data for Context Attribution in Question Answering](https://mlsanity.com/paper/2504.05317/) (2025)
- [Model Editing with Graph-Based External Memory](https://mlsanity.com/paper/2505.18343/) (2025)
- [SafePassage: High-Fidelity Information Extraction with Black Box LLMs](https://mlsanity.com/paper/2510.00276/) (2025)
- [Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs](https://mlsanity.com/paper/2604.13258/) (2026)
- [Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models](https://mlsanity.com/paper/2510.25766/) (2025)
- [Jointly Generating and Attributing Answers using Logits of Document-Identifier Tokens](https://mlsanity.com/paper/2508.08942/) (2025)
- [Citation Failure: Definition, Analysis and Efficient Mitigation](https://mlsanity.com/paper/2510.20303/) (2025)
- [C2-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models](https://mlsanity.com/paper/2602.00004/) (2025)
- [How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.28358/) (2026)
- [MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering](https://mlsanity.com/paper/2607.01420/) (2026)

## Abstract (arXiv)

With the enhancement in the field of generative artificial intelligence (AI), contextual question answering has become extremely relevant. Attributing model generations to the input source document is essential to ensure trustworthiness and reliability. We observe that when large language models (LLMs) are used for contextual question answering, the output answer often consists of text copied verbatim from the input prompt which is linked together with "glue text" generated by the LLM. Motivated by this, we propose that LLMs have an inherent awareness from where the text was copied, likely captured in the hidden states of the LLM. We introduce a novel method for attribution in contextual question answering, leveraging the hidden state representations of LLMs. Our approach bypasses the need for extensive model retraining and retrieval model overhead, offering granular attributions and preserving the quality of generated answers. Our experimental results demonstrate that our method performs on par or better than GPT-4 at identifying verbatim copied segments in LLM generations and in attributing these segments to their source. Importantly, our method shows robust performance across various LLM architectures, highlighting its broad applicability. Additionally, we present Verifiability-granular, an attribution dataset which has token level annotations for LLM generations in the contextual question answering setup.