# Measuring the Similarity of Sentential Arguments in Dialog

arXiv: https://arxiv.org/abs/1709.01887 · HTML: https://mlsanity.com/paper/1709.01887/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2017.

## Built on by (most cited first, 23 of 23)

- [CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations](https://mlsanity.com/paper/2310.11501/) (2023)
- [Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?](https://mlsanity.com/paper/2402.11597/) (2024)
- [Contrastive Learning of Sentence Embeddings from Scratch](https://mlsanity.com/paper/2305.15077/) (2023)
- [Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework](https://mlsanity.com/paper/2210.16798/) (2022)
- [Natural Language Decompositions of Implicit Content Enable Better Text Representations](https://mlsanity.com/paper/2305.14583/) (2023)
- [Key Point Analysis via Contrastive Learning and Extractive Argument Summarization](https://mlsanity.com/paper/2109.15086/) (2021)
- [How Many Data Samples is an Additional Instruction Worth?](https://mlsanity.com/paper/2203.09161/) (2022)
- [Prompting with Pseudo-Code Instructions](https://mlsanity.com/paper/2305.11790/) (2023)
- [Examining Bias in Opinion Summarisation Through the Perspective of Opinion Diversity](https://mlsanity.com/paper/2306.04424/) (2023)
- [Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluation](https://mlsanity.com/paper/2406.03151/) (2024)
- [Sentence Similarity Based on Contexts](https://mlsanity.com/paper/2105.07623/) (2021)
- [Do You Hear The People Sing? Key Point Analysis via Iterative Clustering and Abstractive Summarisation](https://mlsanity.com/paper/2305.16000/) (2023)
- [Enhancing Argument Summarization: Prioritizing Exhaustiveness in Key Point Generation and Introducing an Automatic Coverage Evaluation Metric](https://mlsanity.com/paper/2404.11793/) (2024)
- [Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments](https://mlsanity.com/paper/2505.22137/) (2025)
- [Argument Summarization and its Evaluation in the Era of Large Language Models](https://mlsanity.com/paper/2503.00847/) (2025)
- [Topic Ontologies for Arguments](https://mlsanity.com/paper/2301.09759/) (2023)
- [Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning](https://mlsanity.com/paper/2310.10962/) (2023)
- [A Comparison of Document Similarity Algorithms](https://mlsanity.com/paper/2304.01330/) (2023)
- [Multi-Task Learning Improves Performance In Deep Argument Mining Models](https://mlsanity.com/paper/2307.01401/) (2023)
- [An Empirical Study on Measuring the Similarity of Sentential Arguments with Language Model Domain Adaptation](https://mlsanity.com/paper/2102.09786/) (2021)
- [Accountable Error Characterization](https://mlsanity.com/paper/2105.04707/) (2021)
- [Natural Language Querying System Through Entity Enrichment](https://mlsanity.com/paper/2410.15753/) (2024)
- [Do LLM Debates Repeat Arguments Differently Across Languages?](https://mlsanity.com/paper/2607.23442/) (2026)

## Abstract (arXiv)

When people converse about social or political topics, similar arguments are often paraphrased by different speakers, across many different conversations. Debate websites produce curated summaries of arguments on such topics; these summaries typically consist of lists of sentences that represent frequently paraphrased propositions, or labels capturing the essence of one particular aspect of an argument, e.g. Morality or Second Amendment. We call these frequently paraphrased propositions ARGUMENT FACETS. Like these curated sites, our goal is to induce and identify argument facets across multiple conversations, and produce summaries. However, we aim to do this automatically. We frame the problem as consisting of two steps: we first extract sentences that express an argument from raw social media dialogs, and then rank the extracted arguments in terms of their similarity to one another. Sets of similar arguments are used to represent argument facets. We show here that we can predict ARGUMENT FACET SIMILARITY with a correlation averaging 0.63 compared to a human topline averaging 0.68 over three debate topics, easily beating several reasonable baselines.