Beyond Accuracy: Interpreting Topic Representation in Suicide Ideation Detection Models

• URL: http://arxiv.org/abs/2606.07714v1
• Date: Fri, 05 Jun 2026 14:46:50 GMT
• Title: Beyond Accuracy: Interpreting Topic Representation in Suicide Ideation Detection Models
• Abstract summary: We analyze how suicide detection models encode psychological risk factors in their internal representation space.<n>Our results show that topic-aware augmentation increases the clarity and distinctness of underrepresented psychosocial risk factors.
• Score: 5.390675870849208
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Suicide ideation detection models are typically evaluated using aggregate performance metrics, yet little is known about how they internally represent psychologically meaningful risk factors. In high-stakes mental health applications, understanding these internal representations is essential for safety, transparency, and responsible deployment. In this work, we move beyond accuracy and analyze how suicide detection models trained on original and topic-augmented datasets encode psychological risk factors in their internal representation space. Using visualization and geometric analysis, we examine the coherence and separability of topic-related features. Our results show that topic-aware augmentation increases the clarity and distinctness of underrepresented psychosocial risk factors such as immigration, family issues, and financial crisis. These findings suggest that augmentation not only improves model performance but also leads to more structured and interpretable internal representations.

Related papers

• Profiling User Vulnerability to Phishing Through Psychological and Behavioral Factors [0.7231477812426922]
  This study investigates the multidimensional nature of user susceptibility by analyzing data from the Spamley dataset.<n>Using Exploratory Factor Analysis (EFA), five latent constructs were identified, named: Seniority, Expertise, Creativity, Stability, and Vulnerability.<n>Results suggest that the majority of users fall into the High-Risk category, characterized by hasty evaluation processes and lower critical analysis.
  arXiv  Detail & Related papers  (2026-05-20T14:35:00Z)
• Decomposing and Steering Functional Metacognition in Large Language Models [7.62618887128252]
  We show that large language models maintain a decomposable space of functional metacognitive states.<n>We show that these states are linearly decodable from internal activations and exhibit distinct layer-wise profiles.<n>Our findings suggest that benchmark performance reflects not only task competence but also the activation of specific functional metacognitive states.
  arXiv  Detail & Related papers  (2026-05-09T13:22:47Z)
• On the Privacy of LLMs: An Ablation Study [0.0]
  Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings.<n>We introduce a unified threat model and notation, reproduce a representative set of privacy attacks, and conduct a structured ablation study.
  arXiv  Detail & Related papers  (2026-05-04T06:06:41Z)
• Mechanistic Decoding of Cognitive Constructs in Large Language Models [0.0]
  We propose a Cognitive Reverse-Engineering framework based on Representation Engineering to analyze social-comparison jealousy.<n>By combining appraisal theory with subspaceization, regression-based weighting, and bidirectional causal steering, we isolate and quantify two psychological antecedents of jealousy.<n>Our framework also demonstrates that toxic emotional states can be mechanically detected and surgically suppressed, suggesting a possible route toward representational monitoring and intervention for AI safety in multi-agent environments.
  arXiv  Detail & Related papers  (2026-04-16T03:54:03Z)
• DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios [57.327907850766785]
  characterization of deception across realistic real-world scenarios remains underexplored.<n>We establish DeceptionBench, the first benchmark that systematically evaluates how deceptive tendencies manifest across different domains.<n>On the intrinsic dimension, we explore whether models exhibit self-interested egoistic tendencies or sycophantic behaviors that prioritize user appeasement.<n>We incorporate sustained multi-turn interaction loops to construct a more realistic simulation of real-world feedback dynamics.
  arXiv  Detail & Related papers  (2025-10-17T10:14:26Z)
• Investigating VLM Hallucination from a Cognitive Psychology Perspective: A First Step Toward Interpretation with Intriguing Observations [60.63340688538124]
  Hallucination is a long-standing problem that has been actively investigated in Vision-Language Models (VLMs)<n>Existing research commonly attributes hallucinations to technical limitations or sycophancy bias, where the latter means the models tend to generate incorrect answers to align with user expectations.<n>In this work, we introduce a psychological taxonomy, categorizing VLMs' cognitive biases that lead to hallucinations, including sycophancy, logical inconsistency, and a newly identified VLMs behaviour: appeal to authority.
  arXiv  Detail & Related papers  (2025-07-03T19:03:16Z)
• Aligned Probing: Relating Toxic Behavior and Model Internals [78.20380492883022]
  We introduce aligned probing, a novel interpretability framework that aligns the behavior of language models (LMs)<n>Using this framework, we examine over 20 OLMo, Llama, and Mistral models, bridging behavioral and internal perspectives for toxicity for the first time.<n>Our results show that LMs strongly encode information about the toxicity level of inputs and subsequent outputs, particularly in lower layers.
  arXiv  Detail & Related papers  (2025-03-17T17:23:50Z)
• Explaining Humour Style Classifications: An XAI Approach to Understanding Computational Humour Analysis [0.21847754147782888]
  This paper presents an explainable AI framework for understanding humour style classification.<n>We apply comprehensive XAI techniques to analyse how linguistic, emotional, and semantic features contribute to humour style classification decisions.<n>Our findings contribute to both the theoretical understanding of computational humour analysis and practical applications in mental health, content moderation, and digital humanities research.
  arXiv  Detail & Related papers  (2025-01-06T10:08:56Z)
• Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach [61.04606493712002]
  Susceptibility to misinformation describes the degree of belief in unverifiable claims that is not observable. Existing susceptibility studies heavily rely on self-reported beliefs. We propose a computational approach to model users' latent susceptibility levels.
  arXiv  Detail & Related papers  (2023-11-16T07:22:56Z)
• Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework [83.21732533130846]
  The paper focuses on large in-the-wild databases, i.e., Aff-Wild and Aff-Wild2. It presents the design of two classes of deep neural networks trained with these databases. A novel multi-task and holistic framework is presented which is able to jointly learn and effectively generalize and perform affect recognition.
  arXiv  Detail & Related papers  (2021-03-29T17:36:20Z)
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models [103.64435911083432]
  We present a novel contrastive learning strategy called it Proactive Pseudo-Intervention (PPI) PPI leverages proactive interventions to guard against image features with no causal relevance. We also devise a novel causally informed salience mapping module to identify key image pixels to intervene, and show it greatly facilitates model interpretability.
  arXiv  Detail & Related papers  (2020-12-06T20:30:26Z)

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.