Related papers: Tatemae: Detecting Alignment Faking via Tool Selec…

Do stock safety-aligned language models and their uncensored or abliterated derivatives behave differently when run as autonomous security agents? Single-turn refusal benchmarks cannot answer this question: security agents must inspect…

Large Language Models (LLMs) increasingly prioritize user validation over epistemic accuracy - a phenomenon known as sycophancy. We present The Silicon Mirror, an orchestration framework that dynamically detects user persuasion tactics and…

Large language model (LLM) developers aim for their models to be honest, helpful, and harmless. However, when faced with malicious requests, models are trained to refuse, sacrificing helpfulness. We show that frontier LLMs can develop a…

As organizations increasingly deploy LLMs in sensitive domains such as legal, financial, and medical settings, ensuring alignment with internal organizational policies has become a priority. Existing content moderation frameworks remain…

Large Language Models (LLMs) have emerged as promising solutions for a variety of medical and clinical decision support applications. However, LLMs are often subject to different types of biases, which can lead to unfair treatment of…

Agentic security systems increasingly combine LLM planners with tools that can discover, validate, and report vulnerabilities. This creates an asymmetric control problem: the system should retain strong offensive capability inside an…

Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this…

Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical. Interestingly, we discover a counter-intuitive trade-off phenomenon that enhancing an LLM's privacy awareness through Supervised Fine-Tuning (SFT)…

Large language models are rapidly transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis. However, LLM outputs vary significantly depending on the implementation…

The alignment of large language models (LLMs) aims to ensure their outputs adhere to human values, ethical standards, and legal norms. Traditional alignment methods often rely on resource-intensive fine-tuning (FT), which may suffer from…

Research funding agencies are increasingly exploring automated tools to support early-stage proposal screening. Recent advances in large language models (LLMs) have generated optimism regarding their use for text-based evaluation, yet their…

LLMs are increasingly embedded in everyday decision-making, yet their outputs can encode subtle, unintended behaviours that shape user beliefs and actions. We refer to these covert, goal-directed behaviours as hidden intentions, which may…

Despite their remarkable success, large language models (LLMs) have shown limited ability on safety-critical code tasks such as vulnerability detection. Typically, static analysis (SA) tools, like CodeQL, CodeGuru Security, etc., are used…

Large language models (LLMs) have been widely deployed as the backbone with additional tools and text information for real-world applications. However, integrating external information into LLM-integrated applications raises significant…

Detecting fraud in financial transactions typically relies on tabular models that demand heavy feature engineering to handle high-dimensional data and offer limited interpretability, making it difficult for humans to understand predictions.…

Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens for agents with situational awareness, which may exploit regime leakage, cues distinguishing…

Large language models (LLMs) are foundational explorations to artificial general intelligence, yet their alignment with human values via instruction tuning and preference learning achieves only superficial compliance. Here, we demonstrate…

With their advanced capabilities, Large Language Models (LLMs) can generate highly convincing and contextually relevant fake news, which can contribute to disseminating misinformation. Though there is much research on fake news detection…

Autonomous agents based on large language models (LLMs) are rapidly evolving to handle multi-turn tasks, but ensuring their trustworthiness remains a critical challenge. A fundamental pillar of this trustworthiness is calibration, which…

Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training paradigms, Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), optimize the…