Theory of Mind and Self-Attributions of Mentality are Dissociable in LLMs
arXiv:2603.28925v1 Announce Type: new Abstract: Safety fine-tuning in Large Language Models (LLMs) seeks to suppress potentially harmful forms of mind-attribution such as models asserting their own consciousness or claiming to experience emotions. We investigate whether suppressing mind-attribution tendencies degrades intimately related socio-cognitive abilities such as Theory of Mind (ToM). Through safety ablation and mechanistic analyses of representational similarity, we demonstrate that LLM attributions of mind to themselves and to technological artefacts are behaviorally and mechanistically dissociable from ToM capabilities. Nevertheless, safety fine-tuned models under-attribute mind to non-human animals relative to human baselines and are less likely to exhibit spiritual belief, supp
View PDF HTML (experimental)
Abstract:Safety fine-tuning in Large Language Models (LLMs) seeks to suppress potentially harmful forms of mind-attribution such as models asserting their own consciousness or claiming to experience emotions. We investigate whether suppressing mind-attribution tendencies degrades intimately related socio-cognitive abilities such as Theory of Mind (ToM). Through safety ablation and mechanistic analyses of representational similarity, we demonstrate that LLM attributions of mind to themselves and to technological artefacts are behaviorally and mechanistically dissociable from ToM capabilities. Nevertheless, safety fine-tuned models under-attribute mind to non-human animals relative to human baselines and are less likely to exhibit spiritual belief, suppressing widely shared perspectives regarding the distribution and nature of non-human minds.
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2603.28925 [cs.CL]
(or arXiv:2603.28925v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2603.28925
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Junsol Kim [view email] [v1] Mon, 30 Mar 2026 18:56:02 UTC (1,011 KB)
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
modellanguage modelannounce
Spark-LLM-Eval: A Distributed Framework for Statistically Rigorous Large Language Model Evaluation
arXiv:2603.28769v1 Announce Type: cross Abstract: Evaluating large language models at scale remains a practical bottleneck for many organizations. While existing evaluation frameworks work well for thousands of examples, they struggle when datasets grow to hundreds of thousands or millions of samples. This scale is common when assessing model behavior across diverse domains or conducting comprehensive regression testing. We present Spark-LLM-Eval, a distributed evaluation framework built natively on Apache Spark. The system treats evaluation as a data-parallel problem, partitioningexamplesacrossexecutorsandaggregatingresultswithproperstatistical accounting. Beyond raw throughput, we emphasize statistical rigor: every reported metric includes bootstrap confidence intervals, and model compar
Covertly improving intelligibility with data-driven adaptations of speech timing
arXiv:2603.30032v1 Announce Type: new Abstract: Human talkers often address listeners with language-comprehension challenges, such as hard-of-hearing or non-native adults, by globally slowing down their speech. However, it remains unclear whether this strategy actually makes speech more intelligible. Here, we take advantage of recent advancements in machine-generated speech allowing more precise control of speech rate in order to systematically examine how targeted speech-rate adjustments may improve comprehension. We first use reverse-correlation experiments to show that the temporal influence of speech rate prior to a target vowel contrast (ex. the tense-lax distinction) in fact manifests in a scissor-like pattern, with opposite effects in early versus late context windows; this pattern
PromptForge-350k: A Large-Scale Dataset and Contrastive Framework for Prompt-Based AI Image Forgery Localization
arXiv:2603.29386v1 Announce Type: new Abstract: The rapid democratization of prompt-based AI image editing has recently exacerbated the risks associated with malicious content fabrication and misinformation. However, forgery localization methods targeting these emerging editing techniques remain significantly under-explored. To bridge this gap, we first introduce a fully automated mask annotating framework that leverages keypoint alignment and semantic space similarity to generate precise ground-truth masks for edited regions. Based on this framework, we construct PromptForge-350k, a large-scale forgery localization dataset covering four state-of-the-art prompt-based AI image editing models, thereby mitigating the data scarcity in this domain. Furthermore, we propose ICL-Net, an effective
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Models
Spark-LLM-Eval: A Distributed Framework for Statistically Rigorous Large Language Model Evaluation
arXiv:2603.28769v1 Announce Type: cross Abstract: Evaluating large language models at scale remains a practical bottleneck for many organizations. While existing evaluation frameworks work well for thousands of examples, they struggle when datasets grow to hundreds of thousands or millions of samples. This scale is common when assessing model behavior across diverse domains or conducting comprehensive regression testing. We present Spark-LLM-Eval, a distributed evaluation framework built natively on Apache Spark. The system treats evaluation as a data-parallel problem, partitioningexamplesacrossexecutorsandaggregatingresultswithproperstatistical accounting. Beyond raw throughput, we emphasize statistical rigor: every reported metric includes bootstrap confidence intervals, and model compar
Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives
arXiv:2603.29997v1 Announce Type: new Abstract: Analogical reasoning is a key driver of human generalization in problem-solving and argumentation. Yet, analogies between narrative structures remain challenging for machines. Cognitive engines for structural mapping are not directly applicable, as they assume pre-extracted entities, whereas LLMs' performance is sensitive to prompt format and the degree of surface similarity between narratives. This gap motivates a key question: What is the impact of enhancing structural mapping with LLM-derived abstractions on their analogical reasoning ability in narratives? To that end, we propose a modular framework named YARN (Yielding Abstractions for Reasoning in Narratives), which uses LLMs to decompose narratives into units, abstract these units, and
A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models
arXiv:2603.29676v1 Announce Type: new Abstract: Large vision-language models (LVLMs) achieve impressive performance, yet their internal decision-making processes remain opaque, making it difficult to determine if the success stems from true multimodal fusion or from reliance on unimodal priors. To address this attribution gap, we introduce a novel framework using partial information decomposition (PID) to quantitatively measure the "information spectrum" of LVLMs -- decomposing a model's decision-relevant information into redundant, unique, and synergistic components. By adapting a scalable estimator to modern LVLM outputs, our model-agnostic pipeline profiles 26 LVLMs on four datasets across three dimensions -- breadth (cross-model & cross-task), depth (layer-wise information dynamics), a
StereoVGGT: A Training-Free Visual Geometry Transformer for Stereo Vision
arXiv:2603.29368v1 Announce Type: new Abstract: Driven by the advancement of 3D devices, stereo vision tasks including stereo matching and stereo conversion have emerged as a critical research frontier. Contemporary stereo vision backbones typically rely on either monocular depth estimation (MDE) models or visual foundation models (VFMs). Crucially, these models are predominantly pretrained without explicit supervision of camera poses. Given that such geometric knowledge is indispensable for stereo vision, the absence of explicit spatial constraints constitutes a significant performance bottleneck for existing architectures. Recognizing that the Visual Geometry Grounded Transformer (VGGT) operates as a foundation model pretrained on extensive 3D priors, including camera poses, we investiga
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!