# Prompt, Condition, and Generate: Classification of Unsupported Claims with In-Context Learning

arXiv: https://arxiv.org/abs/2309.10359 · HTML: https://mlsanity.com/paper/2309.10359/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 19 Sep 2023.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Can large language models reason about medical questions?](https://mlsanity.com/paper/2207.08143/) (2022)
- [Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents](https://mlsanity.com/paper/2110.10150/) (2021)
- [Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networks](https://mlsanity.com/paper/1802.05758/) (2018)
- [Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation](https://mlsanity.com/paper/2210.13865/) (2022)
- [Aspect-Controlled Neural Argument Generation](https://mlsanity.com/paper/2005.00084/) (2020)
- [Fine-Grained Argument Unit Recognition and Classification](https://mlsanity.com/paper/1904.09688/) (2019)
- [Exploring the Role of Argument Structure in Online Debate Persuasion](https://mlsanity.com/paper/2010.03538/) (2020)
- [Towards Explainable Fact Checking](https://mlsanity.com/paper/2108.10274/) (2021)
- [A Dataset of General-Purpose Rebuttal](https://mlsanity.com/paper/1909.00393/) (2019)
- [Generating Fact Checking Summaries for Web Claims](https://mlsanity.com/paper/2010.08570/) (2020)
- [A Large-Scale Empirical Study of Geotagging Behavior on Twitter](https://mlsanity.com/paper/1908.10948/) (2019)
- [Harnessing Abstractive Summarization for Fact-Checked Claim Detection](https://mlsanity.com/paper/2209.04612/) (2022)
- [Towards Effective Rebuttal: Listening Comprehension using Corpus-Wide Claim Mining](https://mlsanity.com/paper/1907.11889/) (2019)
- [Searching for Structure in Unfalsifiable Claims](https://mlsanity.com/paper/2209.00495/) (2022)

## Built on by (most cited first, 2 of 2)

- [Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memes](https://mlsanity.com/paper/2501.13851/) (2025)
- [COVIDHealth: A Benchmark Twitter Dataset and Machine Learning based Web Application for Classifying COVID-19 Discussions](https://mlsanity.com/paper/2402.09897/) (2024)

## Abstract (arXiv)

Unsupported and unfalsifiable claims we encounter in our daily lives can influence our view of the world. Characterizing, summarizing, and -- more generally -- making sense of such claims, however, can be challenging. In this work, we focus on fine-grained debate topics and formulate a new task of distilling, from such claims, a countable set of narratives. We present a crowdsourced dataset of 12 controversial topics, comprising more than 120k arguments, claims, and comments from heterogeneous sources, each annotated with a narrative label. We further investigate how large language models (LLMs) can be used to synthesise claims using In-Context Learning. We find that generated claims with supported evidence can be used to improve the performance of narrative classification models and, additionally, that the same model can infer the stance and aspect using a few training examples. Such a model can be useful in applications which rely on narratives , e.g. fact-checking.