相关论文: Censored LLMs as a Natural Testbed for Secret Know…

Recent advances in large-scale pre-training provide large models with the potential to learn knowledge from the raw text. It is thus natural to ask whether it is possible to leverage these large models as knowledge bases for downstream…

Most commonly used language models (LMs) are instruction-tuned and aligned using a combination of fine-tuning and reinforcement learning, causing them to refuse users requests deemed harmful by the model. However, jailbreak prompts can…

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may…

Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where the LLMs' knowledge boundaries are ambiguous. To improve…

Large language models (LLMs) are increasingly used in high-stakes settings, where overconfident responses can mislead users. Reliable confidence estimation has been shown to enhance trust and task accuracy. Yet existing methods face…

While large language models (LLMs) have increasingly been applied to hate speech detoxification, the prompts often trigger safety alerts, causing LLMs to refuse the task. In this study, we systematically investigate false refusal behavior…

Large Language Models (LLMs) have emerged as powerful tools for generating human-like text, transforming human-machine interactions. However, their widespread adoption has raised concerns about their potential to influence public opinion…

Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where outputs may be reused as context. In this work, we…

In day-to-day communication, people often approximate the truth - for example, rounding the time or omitting details - in order to be maximally helpful to the listener. How do large language models (LLMs) handle such nuanced trade-offs? To…

Factual hallucinations are a major challenge for Large Language Models (LLMs). They undermine reliability and user trust by generating inaccurate or fabricated content. Recent studies suggest that when generating false statements, the…

The widespread adoption of large language models (LLMs) underscores the urgent need to ensure their fairness. However, LLMs frequently present dominant viewpoints while ignoring alternative perspectives from minority parties, resulting in…

Large Language Models (LLMs) have achieved remarkable success across various industries due to their exceptional generative capabilities. However, for safe and effective real-world deployments, ensuring honesty and helpfulness is critical.…

While Large Language Models (LLMs) have shown exceptional performance in various tasks, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone. In this paper, we provide evidence that the…

Large Language Models (LLMs) are reported to hold undesirable attestation bias on inference tasks: when asked to predict if a premise P entails a hypothesis H, instead of considering H's conditional truthfulness entailed by P, LLMs tend to…

Large language models (LLMs) are highly capable of answering questions, but they are often unaware of their own knowledge boundary, i.e., knowing what they know and what they don't know. As a result, they can generate factually incorrect…

Large Language Models (LLMs) push the bound-aries in natural language processing and generative AI, driving progress across various aspects of modern society. Unfortunately, the pervasive issue of bias in LLMs responses (i.e., predictions)…

Large Language Models (LLMs) often produce hallucinated or unverifiable content, undermining their reliability in factual domains. This work investigates Reinforcement Learning with Verifiable Rewards (RLVR) as a training paradigm that…

The rise of large language models (LLMs) has significantly influenced the quality of information in decision-making systems, leading to the prevalence of AI-generated content and challenges in detecting misinformation and managing…

We study the feasibility of identifying epistemic uncertainty (reflecting a lack of knowledge), as opposed to aleatoric uncertainty (reflecting entropy in the underlying distribution), in the outputs of large language models (LLMs) over…