Verifiable Social Reasoning for LLM Assistants

• URL: http://arxiv.org/abs/2609.17496v1
• Date: Tue, 15 Sep 2026 17:37:29 GMT
• Title: Verifiable Social Reasoning for LLM Assistants
• Abstract summary: We introduce Fuse, a multi-agent simulation framework for studying user-mediated social reasoning.<n>In Fuse, a target agent with a hidden motive interacts with other agents including one representing the user, who then consults the evaluated assistant to infer the target's motive.<n>Fuse is validated through a human study with 24k annotations.
• Score: 18.879370068754074
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i) it requires setups where the assistant learns about social situations from subjective user narratives, and (ii) social properties, such as others' intentions, typically lack verifiable ground truth. To address these challenges, we introduce Fuse, a multi-agent simulation framework for studying user-mediated social reasoning. In Fuse, a target agent with a hidden motive interacts with other agents including one representing the user, who then consults the evaluated assistant to infer the target's motive, providing verifiable ground truth by construction. Simulation faithfulness is validated through a human study with 24k annotations. We apply Fuse to 12 LLMs and demonstrate its analytical utility by systematically isolating key factors, showing that (i) user mediation compounds the inherent difficulty of social reasoning; (ii) LLMs exhibit systematic sensitivity to biased user framing; (iii) models can require more details than humans need to reach a correct prediction; and (iv) longer conversations do not always improve performance despite providing opportunities for clarifying questions. We open-source Fuse and a dataset with 21k examples.

Related papers

• Verbalizing LLMs' assumptions to explain and control sycophancy [62.927670321859495]
  LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather than providing genuine assessment.<n>We present Verbalized Assumptions, a framework for eliciting these assumptions from LLMs.<n>Our work contributes a new understanding of assumptions as a mechanism for sycophancy.
  arXiv  Detail & Related papers  (2026-04-03T14:15:43Z)
• Debiasing Large Language Models toward Social Factors in Online Behavior Analytics through Prompt Knowledge Tuning [1.357291726431012]
  Attribution theory explains how individuals attribute others' behavior in a social context by employing personal (dispositional) and impersonal (situational) causality.<n>Large Language Models (LLMs), trained on human-generated corpora, may implicitly mimic this social attribution process in social contexts.<n>We introduce a scalable method to mitigate such biases by enriching the instruction prompts for LLMs with two prompt aids using social-attribution knowledge.
  arXiv  Detail & Related papers  (2026-03-28T00:15:40Z)
• Implicit Humanization in Everyday LLM Moral Judgments [0.0]
  Recent adoption of conversational information systems has expanded the scope of user queries to include complex tasks such as personal advice-seeking.<n>We identify a specific type of sought advice-a request for a moral judgment-which carries potentially harmful anthropomorphic projections.<n>In this study, we examine the reinforcement of these assumptions in the responses of four major general-purpose LLMs through the use of linguistic, behavioral, and cognitive anthropomorphic cues.
  arXiv  Detail & Related papers  (2026-03-23T02:48:54Z)
• Who's Asking? Evaluating LLM Robustness to Inquiry Personas in Factual Question Answering [15.641627064295237]
  We evaluate robustness to inquiry personas, i.e. user profiles that convey attributes like identity, expertise, or belief.<n>We find that such cues can meaningfully alter QA accuracy and trigger failure modes such as refusals, hallucinated limitations, and role confusion.
  arXiv  Detail & Related papers  (2025-10-14T18:59:15Z)
• Personalized Reasoning: Just-In-Time Personalization and Why LLMs Fail At It [81.50711040539566]
  Current large language model (LLM) development treats task-solving and preference alignment as separate challenges.<n>We introduce PREFDISCO, an evaluation methodology that transforms static benchmarks into interactive personalization tasks.<n>Our framework creates scenarios where identical questions require different reasoning chains depending on user context.
  arXiv  Detail & Related papers  (2025-09-30T18:55:28Z)
• Teaching Language Models To Gather Information Proactively [53.85419549904644]
  Large language models (LLMs) are increasingly expected to function as collaborative partners.<n>In this work, we introduce a new task paradigm: proactive information gathering.<n>We design a scalable framework that generates partially specified, real-world tasks, masking key information.<n>Within this setup, our core innovation is a reinforcement finetuning strategy that rewards questions that elicit genuinely new, implicit user information.
  arXiv  Detail & Related papers  (2025-07-28T23:50:09Z)
• Bridging Expertise Gaps: The Role of LLMs in Human-AI Collaboration for Cybersecurity [17.780795900414716]
  This study investigates whether large language models (LLMs) can function as intelligent collaborators to bridge expertise gaps in cybersecurity decision-making.<n>We find that human-AI collaboration improves task performance,reducing false positives in phishing detection and false negatives in intrusion detection.
  arXiv  Detail & Related papers  (2025-05-06T04:47:52Z)
• Evaluating Cultural and Social Awareness of LLM Web Agents [113.49968423990616]
  We introduce CASA, a benchmark designed to assess large language models' sensitivity to cultural and social norms.<n>Our approach evaluates LLM agents' ability to detect and appropriately respond to norm-violating user queries and observations.<n>Experiments show that current LLMs perform significantly better in non-agent environments.
  arXiv  Detail & Related papers  (2024-10-30T17:35:44Z)
• AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios [38.878966229688054]
  We introduce AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios. Drawing on Dramaturgical Theory, AgentSense employs a bottom-up approach to create 1,225 diverse social scenarios constructed from extensive scripts. We analyze goals using ERG theory and conduct comprehensive experiments. Our findings highlight that LLMs struggle with goals in complex social scenarios, especially high-level growth needs, and even GPT-4o requires improvement in private information reasoning.
  arXiv  Detail & Related papers  (2024-10-25T07:04:16Z)
• Evaluating Large Language Models with Psychometrics [59.821829073478376]
  This paper offers a comprehensive benchmark for quantifying psychological constructs of Large Language Models (LLMs)<n>Our work identifies five key psychological constructs -- personality, values, emotional intelligence, theory of mind, and self-efficacy -- assessed through a suite of 13 datasets.<n>We uncover significant discrepancies between LLMs' self-reported traits and their response patterns in real-world scenarios, revealing complexities in their behaviors.
  arXiv  Detail & Related papers  (2024-06-25T16:09:08Z)
• How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation [46.42384207122049]
  We design SimulateBench to evaluate the believability of large language models (LLMs) when simulating human behaviors. Based on SimulateBench, we evaluate the performances of 10 widely used LLMs when simulating characters.
  arXiv  Detail & Related papers  (2023-12-28T16:51:11Z)
• Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents [60.27066549589362]
  Social language used by human agents is associated with greater users' responsiveness and task completion. The model uses a sequence-to-sequence deep learning architecture, extended with a social language understanding element. Evaluation in terms of content preservation and social language level using both human judgment and automatic linguistic measures shows that the model can generate responses that enable agents to address users' issues in a more socially appropriate way.
  arXiv  Detail & Related papers  (2020-12-29T08:22:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.