# Unstructured Evidence Attribution for Long Context Query Focused Summarization

arXiv: https://arxiv.org/abs/2502.14409 · HTML: https://mlsanity.com/paper/2502.14409/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 56 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Builds on (most cited first, 30 of 34)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding](https://mlsanity.com/paper/2305.14196/) (2023)
- [Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization](https://mlsanity.com/paper/2406.16008/) (2024)
- [Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems](https://mlsanity.com/paper/2407.01370/) (2024)
- [An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics](https://mlsanity.com/paper/2207.00939/) (2022)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [Eliminating Position Bias of Language Models: A Mechanistic Approach](https://mlsanity.com/paper/2407.01100/) (2024)
- [Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training](https://mlsanity.com/paper/2311.09198/) (2023)
- [Learning to Plan and Generate Text with Citations](https://mlsanity.com/paper/2404.03381/) (2024)
- [Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP](https://mlsanity.com/paper/2407.00402/) (2024)
- [How Far are We from Robust Long Abstractive Summarization?](https://mlsanity.com/paper/2210.16732/) (2022)
- [MDCure: A Scalable Pipeline for Multi-Document Instruction-Following](https://mlsanity.com/paper/2410.23463/) (2024)
- [LexAbSumm: Aspect-based Summarization of Legal Decisions](https://mlsanity.com/paper/2404.00594/) (2024)
- [Measuring Lexical Diversity in Texts: The Twofold Length Problem](https://mlsanity.com/paper/2307.04626/) (2023)

## Built on by (most cited first, 5 of 5)

- [What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models](https://mlsanity.com/paper/2510.04226/) (2025)
- [Stress Testing Factual Consistency Metrics for Long-Document Summarization](https://mlsanity.com/paper/2511.07689/) (2025)
- [Citation Failure: Definition, Analysis and Efficient Mitigation](https://mlsanity.com/paper/2510.20303/) (2025)
- [Summarization is Not Dead Yet](https://mlsanity.com/paper/2606.08000/) (2026)
- [Query-Focused Event Summarization: A Dataset and Benchmark](https://mlsanity.com/paper/2607.11166/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are capable of generating coherent summaries from very long contexts given a user query, and extracting and citing evidence spans helps improve the trustworthiness of these summaries. Whereas previous work has focused on evidence citation with fixed levels of granularity (e.g. sentence, paragraph, document, etc.), we propose to extract unstructured (i.e., spans of any length) evidence in order to acquire more relevant and consistent evidence than in the fixed granularity case. We show how existing systems struggle to copy and properly cite unstructured evidence, which also tends to be "lost-in-the-middle". To help models perform this task, we create the Summaries with Unstructured Evidence Text dataset (SUnsET), a synthetic dataset generated using a novel pipeline, which can be used as training supervision for unstructured evidence summarization. We demonstrate across 5 LLMs and 4 datasets spanning human written, synthetic, single, and multi-document settings that LLMs adapted with SUnsET generate more relevant and factually consistent evidence with their summaries, extract evidence from more diverse locations in their context, and can generate more relevant and consistent summaries than baselines with no fine-tuning and fixed granularity evidence. We release SUnsET and our generation code to the public.