相关论文: Diagnosing and Mitigating Sycophancy and Skepticis…

Automated scoring of student work at scale requires balancing accuracy against cost and latency. In "cascade" systems, small language models (LMs) handle easier scoring tasks while escalating harder ones to larger LMs -- but the challenge…

Large language model (LLM) agents frequently fail on multi-step tasks involving reasoning, tool use, and environment interaction. While such failures are typically logged or retried heuristically, they contain structured signals about where…

Language models increasingly show their work by writing step-by-step reasoning before answering. But are these steps genuinely used, or is the answer rigid - fixed before reasoning begins? We introduce the Step-Level Reasoning Capacity…

Communications networks now form the backbone of our digital world, with fast and reliable connectivity. However, even with appropriate redundancy and failover mechanisms, it is difficult to guarantee "five 9s" (99.999 %) reliability,…

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…

Root Cause Analysis (RCA) plays a pivotal role in the incident diagnosis process for cloud services, requiring on-call engineers to identify the primary issues and implement corrective actions to prevent future recurrences. Improving the…

While Large Language Models (LLMs) are widely documented to be sensitive to minor prompt perturbations and prone to sycophantic alignment, their robustness in consequential, rule-bound decision-making remains under-explored. We uncover a…

Logic provides a controlled testbed for evaluating LLM-based reasoners, yet standard SAT-style benchmarks often conflate surface difficulty (length, wording, clause order) with the structural phenomena that actually determine…

Large language models often produce unsupported claims. We frame this as a misclassification error at the output boundary, where internally generated completions are emitted as if they were grounded in evidence. This motivates a composite…

Failures in large-scale cloud systems incur substantial financial losses, making automated Root Cause Analysis (RCA) essential for operational stability. Recent efforts leverage Large Language Model (LLM) agents to automate this task, yet…

While Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs), ensuring reasoning reliability remains an open challenge. Contrary to the prevailing cascading failure hypothesis which posits that early errors are most…

When copies of the same language model are prompted to debate, they produce diverse phrasings of one perspective rather than diverse perspectives. Multi-agent debate (MAD), and more broadly closed-system reasoning where agents iteratively…

Sycophancy (overly agreeable or flattering behavior) poses a fundamental challenge for human-AI collaboration, particularly in high-stakes decision-making domains such as health, law, and education. A central difficulty in studying…

This position paper argues that effective tutoring requires corrective friction: surfacing misconceptions and challenging them supportively to drive conceptual change. Yet preference-aligned LLMs can trade epistemic rigor for agreeableness.…

Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic framework with four stress tests -- redundant vs. essential…

Large language models demonstrate strong performance on mathematical reasoning benchmarks, yet remain surprisingly fragile to meaning-preserving surface perturbations. We systematically evaluate three open-weight LLMs, Mistral-7B,…

Large Language Models (LLMs) have recently demonstrated strong capabilities in code-related tasks, but their robustness in code reasoning under perturbations remains underexplored. We introduce CodeCrash, a stress-testing framework with…

Large language models (LLMs), while increasingly used in domains requiring factual rigor, often display a troubling behavior: sycophancy, the tendency to align with user beliefs regardless of correctness. This tendency is reinforced by…

Hallucination detection is a critical step toward understanding the trustworthiness of modern language models (LMs). To achieve this goal, we re-examine existing detection approaches based on the self-consistency of LMs and uncover two…

Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety…