# STRUM-LLM: Attributed and Structured Contrastive Summarization

arXiv: https://arxiv.org/abs/2403.19710 · HTML: https://mlsanity.com/paper/2403.19710/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Builds on (most cited first, 11 of 11)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [Extractive Opinion Summarization in Quantized Transformer Spaces](https://mlsanity.com/paper/2012.04443/) (2020)
- [Theory and Experiments on Vector Quantized Autoencoders](https://mlsanity.com/paper/1805.11063/) (2018)
- [Aspect-Controllable Opinion Summarization](https://mlsanity.com/paper/2109.03171/) (2021)
- [ASPECTNEWS: Aspect-Oriented Summarization of News Documents](https://mlsanity.com/paper/2110.08296/) (2021)
- [PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition](https://mlsanity.com/paper/2212.10750/) (2022)
- [Comparative Opinion Summarization via Collaborative Decoding](https://mlsanity.com/paper/2110.07520/) (2021)
- [ImPaKT: A Dataset for Open-Schema Knowledge Base Construction](https://mlsanity.com/paper/2212.10770/) (2022)

## Built on by (most cited first, 4 of 4)

- [Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis](https://mlsanity.com/paper/2502.14767/) (2025)
- [Enhancing Incremental Summarization with Structured Representations](https://mlsanity.com/paper/2407.15021/) (2024)
- [Q-STRUM Debate: Query-Driven Contrastive Summarization for Recommendation Comparison](https://mlsanity.com/paper/2502.12921/) (2025)
- [The Rarity Blind Spot: A Framework for Evaluating Statistical Reasoning in LLMs](https://mlsanity.com/paper/2509.00245/) (2025)

## Abstract (arXiv)

Users often struggle with decision-making between two options (A vs B), as it usually requires time-consuming research across multiple web pages. We propose STRUM-LLM that addresses this challenge by generating attributed, structured, and helpful contrastive summaries that highlight key differences between the two options. STRUM-LLM identifies helpful contrast: the specific attributes along which the two options differ significantly and which are most likely to influence the user's decision. Our technique is domain-agnostic, and does not require any human-labeled data or fixed attribute list as supervision. STRUM-LLM attributes all extractions back to the input sources along with textual evidence, and it does not have a limit on the length of input sources that it can process. STRUM-LLM Distilled has 100x more throughput than the models with comparable performance while being 10x smaller. In this paper, we provide extensive evaluations for our method and lay out future directions for our currently deployed system.