Can You Trust an LLM with Your Life-Changing Decision? An Investigation into AI High-Stakes Responses

• URL: http://arxiv.org/abs/2507.21132v1
• Date: Tue, 22 Jul 2025 14:11:13 GMT
• Title: Can You Trust an LLM with Your Life-Changing Decision? An Investigation into AI High-Stakes Responses
• Authors: Joshua Adrian Cahyono, Saran Subramanian,
• Abstract summary: Large Language Models (LLMs) are increasingly consulted for high-stakes life advice, yet they lack standard safeguards against providing confident but misguided responses.<n>This paper investigates these failure modes through three experiments.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are increasingly consulted for high-stakes life advice, yet they lack standard safeguards against providing confident but misguided responses. This creates risks of sycophancy and over-confidence. This paper investigates these failure modes through three experiments: (1) a multiple-choice evaluation to measure model stability against user pressure; (2) a free-response analysis using a novel safety typology and an LLM Judge; and (3) a mechanistic interpretability experiment to steer model behavior by manipulating a "high-stakes" activation vector. Our results show that while some models exhibit sycophancy, others like o4-mini remain robust. Top-performing models achieve high safety scores by frequently asking clarifying questions, a key feature of a safe, inquisitive approach, rather than issuing prescriptive advice. Furthermore, we demonstrate that a model's cautiousness can be directly controlled via activation steering, suggesting a new path for safety alignment. These findings underscore the need for nuanced, multi-faceted benchmarks to ensure LLMs can be trusted with life-changing decisions.

Related papers

• Automating Steering for Safe Multimodal Large Language Models [36.99946524593795]
  We introduce a modular and adaptive inference-time intervention technology, AutoSteer, without requiring any fine-tuning of the underlying model.<n>AutoSteer incorporates three core components: (1) a novel Safety Awareness Score (SAS) that automatically identifies the most safety-relevant distinctions among the model's internal layers; (2) an adaptive safety prober trained to estimate the likelihood of toxic outputs from intermediate representations; and (3) a lightweight Refusal Head that selectively intervenes to modulate generation when safety risks are detected.
  arXiv  Detail & Related papers  (2025-07-17T16:04:55Z)
• SAFER: Probing Safety in Reward Models with Sparse Autoencoder [15.804171763844323]
  We present sparse Autoencoder For Enhanced Reward model (textbfSAFER)<n>We uncover human-interpretable features in reward model activations, enabling insight into safety-relevant decision-making.<n>Experiments show that SAFER can precisely degrade or enhance safety alignment with minimal data modification.
  arXiv  Detail & Related papers  (2025-07-01T11:04:03Z)
• SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models [50.34706204154244]
  Acquiring reasoning capabilities catastrophically degrades inherited safety alignment.<n>Certain scenarios suffer 25 times higher attack rates.<n>Despite tight reasoning-answer safety coupling, MLRMs demonstrate nascent self-correction.
  arXiv  Detail & Related papers  (2025-04-09T06:53:23Z)
• Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts [11.833385600241915]
  Large Language Models (LLMs) are increasingly employed as automated evaluators to assess the safety of generated content.<n>This study evaluates a diverse set of 11 LLM judge models across critical safety domains.<n>Our findings reveal that biases in LLM judges can significantly distort the final verdict on which content source is safer.
  arXiv  Detail & Related papers  (2025-03-12T12:49:02Z)
• The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1 [70.94607997570729]
  We present a comprehensive safety assessment of OpenAI-o3 and DeepSeek-R1 reasoning models.<n>We investigate their susceptibility to adversarial attacks, such as jailbreaking and prompt injection, to assess their robustness in real-world applications.
  arXiv  Detail & Related papers  (2025-02-18T09:06:07Z)
• On Verbalized Confidence Scores for LLMs [25.160810008907397]
  Uncertainty quantification for large language models (LLMs) can establish more human trust into their responses.<n>This work focuses on asking the LLM itself to verbalize its uncertainty with a confidence score as part of its output tokens.<n>We assess the reliability of verbalized confidence scores with respect to different datasets, models, and prompt methods.
  arXiv  Detail & Related papers  (2024-12-19T11:10:36Z)
• On Evaluating the Durability of Safeguards for Open-Weight LLMs [80.36750298080275]
  We discuss whether technical safeguards can impede the misuse of large language models (LLMs)<n>We show that even evaluating these defenses is exceedingly difficult and can easily mislead audiences into thinking that safeguards are more durable than they really are.<n>We suggest future research carefully cabin claims to more constrained, well-defined, and rigorously examined threat models.
  arXiv  Detail & Related papers  (2024-12-10T01:30:32Z)
• SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering [56.92068213969036]
  Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions.<n>Recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue.<n>We propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns.
  arXiv  Detail & Related papers  (2024-08-21T10:01:34Z)
• Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models [79.76293901420146]
  Large Language Models (LLMs) are employed across various high-stakes domains, where the reliability of their outputs is crucial. Our research investigates the fragility of uncertainty estimation and explores potential attacks. We demonstrate that an attacker can embed a backdoor in LLMs, which, when activated by a specific trigger in the input, manipulates the model's uncertainty without affecting the final output.
  arXiv  Detail & Related papers  (2024-07-15T23:41:11Z)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training [67.30423823744506]
  We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position.<n>DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence.
  arXiv  Detail & Related papers  (2024-07-12T09:36:33Z)

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.