# PreScam: A Benchmark for Predicting Scam Progression from Early Conversations

arXiv: https://arxiv.org/abs/2605.12243 · HTML: https://mlsanity.com/paper/2605.12243/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 56 references that are in the map.
- First posted on arXiv 12 May 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection](https://mlsanity.com/paper/2403.02253/) (2024)
- [Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements](https://mlsanity.com/paper/2502.12904/) (2025)
- [GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation](https://mlsanity.com/paper/2310.00800/) (2023)
- [Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?](https://mlsanity.com/paper/2410.23426/) (2024)
- [ChatSpamDetector: Leveraging Large Language Models for Effective Phishing Email Detection](https://mlsanity.com/paper/2402.18093/) (2024)
- [Measure-Observe-Remeasure: An Interactive Paradigm for Differentially-Private Exploratory Analysis](https://mlsanity.com/paper/2406.01964/) (2024)
- [Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents](https://mlsanity.com/paper/2601.22311/) (2026)
- [Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering](https://mlsanity.com/paper/2210.02933/) (2022)
- [Self-Supervised Graph Structure Refinement for Graph Neural Networks](https://mlsanity.com/paper/2211.06545/) (2022)
- [PhishAgent: A Robust Multimodal Agent for Phishing Webpage Detection](https://mlsanity.com/paper/2408.10738/) (2024)
- [The Anatomy of a Cryptocurrency Pump-and-Dump Scheme](https://mlsanity.com/paper/1811.10109/) (2018)
- [Personalized Attacks of Social Engineering in Multi-turn Conversations: LLM Agents for Simulation and Detection](https://mlsanity.com/paper/2503.15552/) (2025)
- [TeleAntiFraud-28k: An Audio-Text Slow-Thinking Dataset for Telecom Fraud Detection](https://mlsanity.com/paper/2503.24115/) (2025)
- [Cognitive Triaging of Phishing Attacks](https://mlsanity.com/paper/1905.02162/) (2019)
- [PsyScam: A Benchmark for Psychological Techniques in Real-World Scams](https://mlsanity.com/paper/2505.15017/) (2025)
- [Dial One for Scam: A Large-Scale Analysis of Technical Support Scams](https://mlsanity.com/paper/1607.06891/) (2016)
- [An Explorative Study of Pig Butchering Scams](https://mlsanity.com/paper/2412.15423/) (2024)
- [Victim as a Service: Designing a System for Engaging with Interactive Scammers](https://mlsanity.com/paper/2510.23927/) (2025)

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

- [The Collaboration Tax: How Much LLM Multi-Agent Systems Pay to Coordinate](https://mlsanity.com/paper/2608.22152/) (2026)
- [Anatomy of a Scam Call: What 10,000 real scam and spam calls reveal about how phone scammers operate](https://mlsanity.com/paper/2608.24127/) (2026)

## Abstract (arXiv)

Conversational scams, such as romance and investment scams, are emerging as a major form of online fraud. Unlike one-shot scam lures such as fake lottery or unpaid toll messages, they unfold through multi-turn conversations in which scammers gradually manipulate victims using evolving psychological techniques. However, existing research mainly focuses on static scam detection or synthetic scams, leaving open whether language models can understand how real-world scams progress over time. We introduce PreScam, a benchmark for modeling scam progression from early conversations. Built from user-submitted scam reports, PreScam filters and structures 177,989 raw reports into 11,573 conversational scam instances spanning 20 scam categories. Each instance is hierarchically structured according to the scam lifecycle defined by the proposed scam kill chain, and further annotated at the turn level with scammer psychological actions and victim responses. We benchmark models on two tasks: real-time termination prediction, which estimates whether a conversation is approaching the termination stage, and scammer action prediction, which forecasts the scammer's subsequent actions. Results show a clear gap between surface-level fluency and progression modeling: supervised encoders substantially outperform zero-shot LLMs on real-time termination prediction, while next-action prediction remains only moderately successful even for strong LLMs. Taken together, these results show that current models can capture some scam-related cues, yet still struggle to track how risk escalates and how manipulation unfolds across turns.