Cover Image

Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Park, Eunkyu, Deng, Wesley Hanwen, Varadarajan, Vasudha, Yan, Mingxi, Kim, Gunhee, Sap, Maarten, Eslami, Motahhare
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Human-Computer Interaction
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations
by: Park, Eunkyu, et al.
Published: (2025)

MM-SCALE: Grounded Multimodal Moral Reasoning via Scalar Judgment and Listwise Alignment
by: Park, Eunkyu, et al.
Published: (2026)

MIRAGE: Multi-model Interface for Reviewing and Auditing Generative Text-to-Image AI
by: Maldaner, Matheus Kunzler, et al.
Published: (2025)

Comprehension Is a Double-Edged Sword: Over-Interpreting Unspecified Information in Intelligible Machine Learning Explanations
by: Xuan, Yueqing, et al.
Published: (2023)

Seeing Twice: How Side-by-Side T2I Comparison Changes Auditing Strategies
by: Maldaner, Matheus Kunzler, et al.
Published: (2025)

Vipera: Towards systematic auditing of generative text-to-image models at scale
by: Huang, Yanwei, et al.
Published: (2025)

"I Don't Think RAI Applies to My Model'' -- Engaging Non-champions with Sticky Stories for Responsible AI Work
by: Nahar, Nadia, et al.
Published: (2025)

WeAudit: Scaffolding User Auditors and AI Practitioners in Auditing Generative AI
by: Deng, Wesley Hanwen, et al.
Published: (2025)

Vipera: Blending Visual and LLM-Driven Guidance for Systematic Auditing of Text-to-Image Generative AI
by: Huang, Yanwei, et al.
Published: (2025)

PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI
by: Deng, Wesley Hanwen, et al.
Published: (2026)

Investigating Youth AI Auditing
by: Solyst, Jaemarie, et al.
Published: (2025)

Examining the Effect of Explanations of AI Privacy Redaction in AI-mediated Interactions
by: Kaushik, Roshni, et al.
Published: (2026)

Strategies for Designing Responsibly within a Capitalist Enterprise
by: Xie, Shixian, et al.
Published: (2026)

Explainable AI as a Double-Edged Sword in Dermatology: The Impact on Clinicians versus The Public
by: Xu, Xuhai, et al.
Published: (2025)

Diversity's Double-Edged Sword: Analyzing Race's Effect on Remote Pair Programming Interactions
by: Mason, Shandler A., et al.
Published: (2024)

PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming
by: Deng, Wesley Hanwen, et al.
Published: (2025)

The Generative AI Ethics Playbook
by: Smith, Jessie J., et al.
Published: (2024)

The Double-Edged Sword of Open-Ended Interaction: How LLM-Driven NPCs Affect Players' Cognitive Load and Gaming Experience
by: Hsu, Ting-Chen, et al.
Published: (2026)

The Double-Edged Sword of Behavioral Responses in Strategic Classification: Theory and User Studies
by: Ebrahimi, Raman, et al.
Published: (2024)

Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences
by: Zheng, Mingqian, et al.
Published: (2025)

Breaking Political Filter Bubbles via Social Comparison
by: Soliman, Nouran, et al.
Published: (2024)

Children's Overtrust and Shifting Perspectives of Generative AI
by: Solyst, Jaemarie, et al.
Published: (2024)

Supporting Industry Computing Researchers in Assessing, Articulating, and Addressing the Potential Negative Societal Impact of Their Work
by: Deng, Wesley Hanwen, et al.
Published: (2024)

The Fall of an Algorithm: Characterizing the Dynamics Toward Abandonment
by: Johnson, Nari, et al.
Published: (2024)

Troubling Taxonomies in GenAI Evaluation
by: Berman, Glen, et al.
Published: (2024)

When the Chain Breaks: Interactive Diagnosis of LLM Chain-of-Thought Reasoning Errors
by: Chen, Shiwei, et al.
Published: (2026)

'Simulacrum of Stories': Examining Large Language Models as Qualitative Research Participants
by: Kapania, Shivani, et al.
Published: (2024)

Framing an AI with Values Reduces AI Reliance in AI-supported Writing Tasks
by: Gao, Alice, et al.
Published: (2026)

What Comes After Harm? Mapping Reparative Actions in AI through Justice Frameworks
by: Xiao, Sijia, et al.
Published: (2025)

Counterspeakers' Perspectives: Unveiling Barriers and AI Needs in the Fight against Online Hate
by: Mun, Jimin, et al.
Published: (2024)

Public Technologies Transforming Work of the Public and the Public Sector
by: Kim, Seyun, et al.
Published: (2024)

Legacy Procurement Practices Shape How U.S. Cities Govern AI: Understanding Government Employees' Practices, Challenges, and Needs
by: Johnson, Nari, et al.
Published: (2024)

Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models
by: Pang, Rock Yuren, et al.
Published: (2025)

"I Just Don't Want My Work Being Fed Into The AI Blender": Queer Artists on Refusing and Resisting Generative AI
by: Taylor, Jordan, et al.
Published: (2026)

User-Driven Value Alignment: Understanding Users' Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions
by: Fan, Xianzhe, et al.
Published: (2024)

The Legend of Holy Sword: An Immersive Experience for Concentration Enhancement
by: Asahi, Hirosuke, et al.
Published: (2024)

Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty
by: Zhou, Kaitlyn, et al.
Published: (2024)

Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective
by: Wang, Qiaosi, et al.
Published: (2025)

"It Might be Technically Impressive, But It's Practically Useless to us": Motivations, Practices, Challenges, and Opportunities for Cross-Functional Collaboration around AI within the News Industry
by: Xiao, Qing, et al.
Published: (2024)

Not Like Us, Hunty: Measuring Perceptions and Behavioral Effects of Minoritized Anthropomorphic Cues in LLMs
by: Basoah, Jeffrey, et al.
Published: (2025)