# How Much Does Persuasion Strategy Matter? LLM-Annotated Evidence from Charitable Donation Dialogues

arXiv: https://arxiv.org/abs/2604.19783 · HTML: https://mlsanity.com/paper/2604.19783/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 13 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Builds on (most cited first, 3 of 3)

- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [Automated Annotation with Generative AI Requires Validation](https://mlsanity.com/paper/2306.00176/) (2023)

## Built on by (most cited first, 1 of 1)

- [Simulated Customers Never Walk Away: Decision Fidelity of LLM User Simulators Measured Against Real Purchase Outcomes](https://mlsanity.com/paper/2606.20708/) (2026)

## Abstract (arXiv)

Which persuasion strategies, if any, are associated with donation compliance? Answering this requires fine-grained strategy labels across a full corpus and statistical tests corrected for multiple comparisons. We annotate all 10,600 persuader turns in the 1,017-dialogue PersuasionForGood corpus (Wang et al., 2019), where donation outcomes are directly observable, with a taxonomy of 41 strategies in 11 categories, using three open-source large language models (LLMs; Qwen3:30b, Mistral-Small-3.2, Phi-4). Strategy categories alone explain little variance in donation outcome (pseudo R2 ≈ 0.015, consistent across all three annotators). Guilt Induction is the only strategy significantly associated with lower donation rates (Delta ≈ -23 percentage points), an effect that replicates across all three models despite only moderate inter-model agreement. Reciprocity is the most robust positive correlate. Target sentiment and interest predict whether a donation occurs but show at most a weak correlation with donation amount. These findings suggest that strategy identification alone is insufficient to explain persuasion effectiveness, and that guilt-based appeals may be counterproductive in prosocial settings. We release the fully annotated corpus as a public resource.