← Back to all news
arXiv Computation and Language

Detecting Conversational Mental Manipulation with Intent-Aware Prompting

The paper introduces Intent‑Aware Prompting (IAP), a new method that uses large language models to detect mental manipulation in conversations by identifying the underlying intents of participants. Experiments on the MentalManip dataset show that IAP outperforms other prompting strategies, especially by reducing false negatives and improving detection of subtle manipulative tactics. The authors provide the code for reproducibility.

Related stories

arXiv Computation and Language
Aug 28

INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment

The paper introduces INTENT-AS-A-TOOL, a method that equips large language models with intent-targeted tools to provide a fine-grained, judge‑free signal of their commitment to specific behaviors during reasoning. By monitoring the probability of calling these intent tools, the authors can track how intent evolves throughout generation, complementing chain‑of‑thought monitoring and expanding post‑hoc labels into dense trajectories. The approach identifies critical steps for online intervention, demonstrating that action preferences are useful for detecting agentic misalignment in autonomous agents.

By Yutong Zhang, Jianshuo Dong, Peng Xu, Long Wang, Jie Zhang, Tianwei Zhang, Xiaoping Zhang, Han Qiu
llmsagentssafety
More like this →
arXiv AI
Aug 6

Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models

arXiv:2503. 15560v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly vulnerable to sophisticated multi-turn manipulation attacks, where adversaries strategically build context through seemingly benign conversational turns to circumvent safety measures and elicit harmful or unauthorized responses.

By Prashant Kulkarni, Assaf Namer
llmsragroboticssafety
More like this →
arXiv Computation and Language
Sep 18

Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue

The paper introduces UC-Bench, a human‑annotated benchmark for detecting user‑side implicit conflicts in Human‑LLM dialogue, a problem largely overlooked compared to LLM‑side conflicts. Experiments show current LLMs struggle with these conflicts, especially when they stem from implicit incompatibilities in dialogue history. To address this, the authors propose SynUC, a constraint‑guided data synthesis method that generates a new training set, UC‑Data, which improves performance of lightweight LLMs on UC‑Bench compared to larger general‑purpose models and existing synthesis approaches.

By Jinqiang Wang, Tao Zhu, Huansheng Ning
llmsbenchmarks
More like this →
arXiv AI
Sep 24

Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness

The paper introduces Safety Nudges, a browser-based tool that displays lightweight, in situ flags when a conversational AI exhibits risky behavior such as hallucination or overconfidence. In a two‑week field study with 45 frequent chatbot users, participants reported that the nudges were useful, clear, and minimally disruptive, and most felt more aware of potential AI harms. However, increased awareness did not automatically translate into measurable changes in user behavior, underscoring the need for relevance, calibration, and user control in nudge design.

By Varshini Elangovan, James Wedgwood, Chhavi Yadav, William Agnew, Sauvik Das, Virginia Smith
safety
More like this →