Mediation

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 30

All topics

Tool Mediation Alters Refusal Mechanisms in Large Language Models
Sep 28, 2026Abel Rodríguez, Giuseppe Garofalo, Lieven Desmet +1Large Language Models Fail Refusals
DistriNet, KU Leuven
ProMediConv: Benchmarking Proactive Conversational Agents in Legal Dispute Mediation
Sep 11, 2026Zesheng Wei, Mengfan Li, Wenhao Liu +3Mediation Dialogue Benchmarks
University of Science and Technology of China · Singapore Management University · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center
MOONWALK: Mediating Operations with Intent-Evidence-Action Alignment Across Junior-Supervisor Review Workflows in Animation/VFX Pre-Production
Sep 9, 2026Shih-Yu Lai, Wen-Fan Wang, Sai Ling +3Agentic Workflow Design Creativity
National Taiwan University, Taipei, Taiwan · MoonShine Animation Studio, Taipei, Taiwan · Cornell Tech, New York City, USA +1
Auditable Release Control for Pedagogical Leakage in LLM Tutors
Aug 1, 2026Nizam KadirData Leakage Release
Science, Mathematics and Technology Singapore University of Technology and Design (SUTD) Singapore
Position, Not Provenance: Separating Reasoning Mediation from Sycophancy in Medical Vision-Language Models
Jul 29, 2026Supratik Bhowal, Subhrajyoti Basu, Aritra Gir Mahanta +1Medical Vision-Language Models Clinical Reasoning Training
Department of Computer Science (AIML) IEM Kolkata, School of UEMK Kolkata, India · Department of Computer Science and Business System Heritage Institute of Technology Kolkata, India · Department of Computer Science and Engineering Indian Institute of Information Technology, Kalyani Kalyani, India
Polistemics: Evaluating LLMs as Information Mediators in Politics & Elections
Jul 28, 2026Baran Peters, Gabor Hollbeck, Robert Jakob +1Political Discourse Epistemic State Replication
ETH Agentic Systems Lab · CORDA
Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales
Jul 28, 2026Genliang Zhu, Chu WangAuthorization Mediation
Accentrust · Georgia Institute of Technology · University of Illinois Urbana-Champaign
Extended Reality as a Mediation Layer for Situated Human Control in Human-Robot Teaming
Jul 27, 2026Jens Grubert, John Dudley, Eyal Ofek +1Human Agency Surgical Robots
Coburg University of Applied Sciences and Arts · University of Cambridge · University of Birmingham
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
Jul 23, 2026Linjun LiEmotional Manipulation Mediation
Department of Mathematics, University of Pennsylvania, Philadelphia, PA.
Just A Rather Very Intelligent Spoken Agent
Jul 18, 2026Chen Chen, Zhehuai ChenMediation Dialogue Benchmarks
NVIDIA
Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration
Jul 15, 2026Justin BronderHonesty Verdict
Corabo Inc.
A Model for Mediating Multi-Modal Human Intent into Safe Maneuvers for UAVs
Jul 13, 2026Sofia Nelson, Dalal Alrajeh, Pedro Antonio Alarcon Granadeno +1Multi-Uav Unmanned Aerial Vehicles
University of Notre Dame Notre Dame, IN, USA · Imperial College London London, UK
When the Target Domain Changes: AI-Mediated Construct Drift in High-Stakes English Language AssessmenW
Jul 13, 2026Yi GuiComputerized Adaptive Testing Interpretive Layer
Measurement Incorporated
Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study
Jul 9, 2026Eugene Ng Yi Sheng, Bingquan ShenMulti-Agent Simulations Mediation
DSO National Laboratories · National University of Singapore
When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games
Jul 6, 2026Jerick Shi, Terry Jingcheng Zhang, Bernhard Schölkopf +2Autonomous Agents Deliberation
Carnegie Mellon University, Pittsburgh, USA · Jinesis AI Lab, Vector Institute and University of Toronto, Toronto, Canada · EuroSafeAI +1
Textual Belief States for World Models: Identifiable Representation Learning Under Strict Mediation
Jun 26, 2026Xiang Gao, Kaiwen Dong, Yuguang Yao +2Intermediate Latent States World Models
Intuit AI Research
The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
Jun 25, 2026Sankaran Vaidyanathan, David Arbour, Aaron Mueller +2Causal Mediation Analysis Mechanistic Interpretability
University of Massachusetts Amherst · Adobe Research · Boston University
Automated Mediator for Human Negotiation: Pre-Mediation via a Structured LLM Pipeline
Jun 9, 2026Jamie Bergen, Sarit KrausMediation Negotiation
Harness Engineering for Physical AI: Robot Middleware Is the Harness Layer
Jun 8, 2026Sanghoon Lee, Jiyeong Chae, Kyung-Joon ParkAgent Harness Robot Systems
Daegu Gyeongbuk Institute of Science and Technology (DGIST) · Daegu, Republic of Korea
MediEncoder: Nonlinear Representation Learning for High-Dimensional Causal Mediation Analysis
Jun 5, 2026Shi Bo, Debarghya Mukherjee, AmirEmad GhassamiCausal Mediation Analysis Mediation
Department of Mathematics and Statistics, Boston University
Forgive or forget: Understanding the context of hate in audio retrieval systems
Jun 4, 2026Arghya Pal, Sailaja Rajanala, Raphael C. -W. Phan +1Text-To-Audio Harmful Language
School of Information Technology, Monash University, Malaysia campus · University of Groningen, the Netherlands
It's not the Language Model, it's the Tool: Deterministic Mediation for Scientific Workflows
May 13, 2026Marios Adamidis, Danae Katrisioti, Yannis Tzitzikas +1Scientific Workflows Reproducibility
Department of Materials Science and Technology, University of Crete, Heraklion, Greece · Institute of Electronic Structure and Laser, FORTH, Heraklion, Greece · Computer Science Department, University of Crete, Heraklion, Greece +2
SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition
May 5, 2026Ruichu Cai, Juntao Gan, Miao Mai +2Named-Entity Recognition Mediation
School of Computer Science, Guangdong University of Technology · Peng Cheng Laboratory · Nanfang Media Group(Nanfang Daily) +1
Distributional Causal Mediation via Conditional Generative Modeling
May 3, 2026Jinlun Zhang, Haoneng Huang, Zishu Zhan +1Causal Mediation Analysis Mediation
State Key Laboratory of Multi-organ Injury Prevention and Treatment, Department of Biostatistics, Guangdong Provincial Key Laboratory of Tropical Disease Research, School of Public Health, Southern Medical University, Guangzhou, China
MILD: Mediator Agent System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration
May 2, 2026Jiyao Wang, Yunbiao Wang, Yubo Jiao +6Automated Vehicles Model-Based Multi-Agent Systems
Department of Civil Engineering, McGill University, Montreal H3A 0G4, Quebec, Canada · Systems Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, Guangdong, China · Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg L-4365, Luxembourg
Architectural Design Decisions in AI Agent Harnesses
Apr 20, 2026Hu WeiProduction Agentic Systems Mediation
CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution
Apr 18, 2026Shutong Jin, Ruiyi Guo, Ray C. C. CheungArtificial Intelligence Agents Mediation
City University of Hong Kong, Hong Kong · Beijing Foreign Studies University
SMaRT: Online Reusable Resource Assignment and an Application to Mediation in the Kenyan Judiciary
Feb 20, 2026Shafkat Farabi, Didac Marti Pinto, Wei Lu +4Repair-Assignment Problem Mediation
Virginia Tech · University College London · The World Bank
Multiply Robust Causal Mediation Analysis with Continuous Treatments
May 19, 2021Yizhen Xu, AmirEmad Ghassami, Numair Sani +1Causal Mediation Analysis Heterogeneous Treatment Effects
Division of Biostatistics, Department of Population Health Sciences, University of Utah, USA · Department of Mathematics and Statistics, Boston University, USA · Department of Computer Science, Johns Hopkins University, USA
BodhiPromptShield: Pre-Inference Prompt Mediation for Surface-Form Privacy Propagation in LLM Agent Pipelines
Date pendingBo Ma, Jinsong Wu, Weiqi YanPrivacy Mediation
Auckland University of Technology Auckland, New Zealand · Guilin University of Electronic Technology Guilin, China

Sep 28, 2026, cs.AIJ/K move · Enter open · S save

Tool Mediation Alters Refusal Mechanisms in Large Language Models

Abel Rodríguez, Giuseppe Garofalo, Lieven Desmet, Vera Rimmer

DistriNet, KU Leuven

Large Language Models Fail Refusals Mediation Harms

Open paper AskPDF arXiv

Large language models (LLMs) are increasingly deployed with access to external tools, yet harmful tool-mediated interactions are less likely to be refused when compared to regular conversational ones. As this change in refusal behavior remains underexplored, we investigate its underlying mechanisms across a diverse set of open-weight language models. We find that information about the harmfulness of a request remains strongly encoded in the model's representations and transfers across conversational and tool-mediated inputs. Evidence from representation geometry and neuron-level analysis further indicates that the two interaction modes systematically distribute harm-related computation differently. Crucially, while conversational inputs can be refused at relatively low levels of perceived harmfulness, tool-mediated inputs remain permissive until harmfulness crosses a substantially higher effective refusal threshold. Moreover, tool-mediated refusal is also more brittle: progressively weakening the refusal computation disrupts tool-mediated refusal at lower intervention strengths than conversational refusal, even when benign capabilities remain intact. Together, our findings indicate that tool mediation does not simply reduce the internal perception of harm, but instead impacts its conversion into refusal. Overall, this suggests tool-mediated environments may intrinsically reduce robustness of models to harmful requests, and that conventional safety evaluations may not fully transfer to LLM agents.

Momentum

Related topics

Latest papers 30