World PulseNow
Newsletter

What About the Scene with the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency Via Adversarial Nudge

arXiv — cs.CL•Thursday, November 13, 2025 at 5:00:00 AM
NegativeArtificial Intelligence
The recent paper on arXiv presents a framework for assessing the factual fidelity of large language models (LLMs) against adversarial nudges, a critical issue as these models are widely used for information retrieval. The study evaluated five prominent LLMs—Claude, GPT, Grok, Gemini, and DeepSeek—across domains of movies and novels. Results indicated a troubling range of susceptibility, with Claude demonstrating strong resilience, while Gemini and DeepSeek showed weak resilience. This disparity in performance underscores the need for caution in deploying LLMs, especially given their growing use in high-stakes contexts where accuracy is paramount. The findings serve as a wake-up call for developers and users alike, emphasizing the importance of rigorous testing and validation to ensure the reliability of these AI systems.
— via World Pulse Now AI Editorial System
Read Original

Was this article worth reading? Share it

Recommended Readings
Disney star debuts AI avatars of the dead
The Rundown AIa day ago
Disney star debuts AI avatars of the dead
NeutralArtificial Intelligence
Disney star has introduced AI avatars representing deceased individuals, marking a significant development in the intersection of entertainment and artificial intelligence. This debut showcases the potential of AI technology to create lifelike representations of those who have passed away, raising questions about ethics and the future of digital personas. The event took place on November 17, 2025, and is expected to attract attention from both fans and industry experts alike.
Read full article
via The Rundown AI
Scaling Latent Reasoning via Looped Language Models
arXiv — cs.CL2 days ago
Scaling Latent Reasoning via Looped Language Models
PositiveArtificial Intelligence
The article presents Ouro, a family of pre-trained Looped Language Models (LoopLM) designed to enhance reasoning capabilities during the pre-training phase. Unlike traditional models that rely on explicit text generation, Ouro incorporates iterative computation in latent space and an entropy-regularized objective for depth allocation. The models, Ouro 1.4B and 2.6B, demonstrate superior performance, matching results of larger state-of-the-art models while emphasizing improved knowledge manipulation rather than increased capacity.
Read full article
via arXiv — cs.CL
Expert-Guided Prompting and Retrieval-Augmented Generation for Emergency Medical Service Question Answering
arXiv — cs.CL2 days ago
Expert-Guided Prompting and Retrieval-Augmented Generation for Emergency Medical Service Question Answering
PositiveArtificial Intelligence
Large language models (LLMs) have shown potential in medical question answering but often lack the domain-specific expertise required in emergency medical services (EMS). The study introduces EMSQA, a dataset with 24.3K questions across 10 clinical areas and 4 certification levels, along with knowledge bases containing 40K documents and 2M tokens. It also presents Expert-CoT and ExpertRAG, strategies that enhance performance by integrating clinical context, resulting in improved accuracy and exam pass rates for EMS certification.
Read full article
via arXiv — cs.CL
Can LLMs Detect Their Own Hallucinations?
arXiv — cs.CL2 days ago
Can LLMs Detect Their Own Hallucinations?
PositiveArtificial Intelligence
Large language models (LLMs) are capable of generating fluent responses but can sometimes produce inaccurate information, referred to as hallucinations. A recent study investigates whether these models can recognize their own inaccuracies. The research formulates hallucination detection as a classification task and introduces a framework utilizing Chain-of-Thought (CoT) to extract knowledge from LLM parameters. Experimental results show that GPT-3.5 Turbo with CoT detected 58.2% of its own hallucinations, suggesting that LLMs can identify inaccuracies if they possess sufficient knowledge.
Read full article
via arXiv — cs.CL
Reinforcing Stereotypes of Anger: Emotion AI on African American Vernacular English
arXiv — cs.CL2 days ago
Reinforcing Stereotypes of Anger: Emotion AI on African American Vernacular English
NegativeArtificial Intelligence
Automated emotion detection systems are increasingly utilized in various fields, including mental health and hiring. However, these models often fail to accurately recognize emotional expressions in dialects like African American Vernacular English (AAVE) due to reliance on dominant cultural norms. A study analyzing 2.7 million tweets from Los Angeles found that emotion recognition models exhibited significantly higher false positive rates for anger in AAVE compared to General American English (GAE), highlighting the limitations of current emotion AI technologies.
Read full article
via arXiv — cs.CL
From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems
arXiv — cs.CL2 days ago
From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems
NeutralArtificial Intelligence
The article investigates the impact of task framing on the conviction of large language models (LLMs) in dialogue systems. It explores how LLMs assess tasks requiring social judgment, contrasting their performance on factual queries with conversational judgment tasks. The study reveals that reframing a task can significantly alter an LLM's judgment, particularly under conversational pressure, highlighting the complexities of LLM decision-making in social contexts.
Read full article
via arXiv — cs.CL
Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
arXiv — cs.CL2 days ago
Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
PositiveArtificial Intelligence
The article presents Thinker, a hierarchical thinking model designed to enhance the reasoning capabilities of large language models (LLMs) through multi-turn interactions. Unlike previous methods that relied on end-to-end reinforcement learning without supervision, Thinker allows for a more structured reasoning process by breaking down complex problems into manageable sub-problems. Each sub-problem is represented in both natural language and logical functions, improving the coherence and rigor of the reasoning process.
Read full article
via arXiv — cs.CL
PustakAI: Curriculum-Aligned and Interactive Textbooks Using Large Language Models
arXiv — cs.CL2 days ago
PustakAI: Curriculum-Aligned and Interactive Textbooks Using Large Language Models
PositiveArtificial Intelligence
PustakAI is a framework designed to create interactive textbooks aligned with the NCERT curriculum for grades 6 to 8 in India. Utilizing Large Language Models (LLMs), it aims to enhance personalized learning experiences, particularly in areas with limited educational resources. The initiative addresses challenges in adapting LLMs to specific curricular content, ensuring accuracy and pedagogical relevance.
Read full article
via arXiv — cs.CL