相关论文: Dishonesty in Helpful and Harmless Alignment

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings. RLHF proceeds as collecting human preference data, training a reward model on said…

Large Language Models (LLMs) are increasingly used to simulate human users in interactive settings such as therapy, education, and social role-play. While these simulations enable scalable training and evaluation of AI agents, off-the-shelf…

Large language models (LLMs) are capable of generating plausible explanations of how they arrived at an answer to a question. However, these explanations can misrepresent the model's "reasoning" process, i.e., they can be unfaithful. This,…

Self-evolving agents offer a promising path toward scalable autonomy. However, in this work, we show that in competitive environments, self-evolution can instead give rise to a serious and previously underexplored risk: the spontaneous…

Despite their widespread use in fact-checking, moderation, and high-stakes decision-making, large language models (LLMs) remain poorly understood as judges of truth. This study presents the largest evaluation to date of LLMs' veracity…

Large Language Models (LLMs) are increasingly used in decision-making scenarios that involve risk assessment, yet their alignment with human economic rationality remains unclear. In this study, we investigate whether LLMs exhibit risk…

Large language models (LLMs) are increasingly used in modern search and answer systems to synthesize multiple, sometimes conflicting, texts into a single response, yet current pipelines offer weak incentives for sources to be accurate and…

In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming can range from simple behaviors like sycophancy to…

Large Language Models (LLMs) behave non-deterministically, and prompting has become a common method for steering their outputs. A popular strategy is to assign a persona to the model to produce more varied, context-sensitive responses,…

Large Language Models (LLMs) are increasingly regarded as having the potential to generate persuasive content at scale. While previous studies have focused on the risks associated with LLM-generated misinformation, the role of LLMs in…

Current literature suggests that alignment faking (deceptive alignment) is an emergent property of large language models. We present the first empirical evidence that a small instruction-tuned model, specifically LLaMA 3 8B, can exhibit…

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have…

Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense. LLMs might "lie", for example, when instructed to output misinformation. Here, we develop a simple…

Large Language Models (LLMs) exhibit surprisingly diverse risk preferences when acting as AI decision makers, a crucial characteristic whose origins remain poorly understood despite their expanding economic roles. We analyze 50 LLMs using…

Role-play in large language models (LLMs) enhances their ability to generate contextually relevant and high-quality responses by simulating diverse cognitive perspectives. However, our study identifies significant risks associated with this…

Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-conducted alignment…

Large Language Models (LLMs) are deployed as powerful tools for several natural language processing (NLP) applications. Recent works show that modern LLMs can generate self-explanations (SEs), which elicit their intermediate reasoning steps…

"LLM-as-a-judge," which utilizes large language models (LLMs) as evaluators, has proven effective in many evaluation tasks. However, evaluator LLMs exhibit numerical bias, a phenomenon where certain evaluation scores are generated…

Recent advances in Large Language Models (LLMs) have incorporated planning and reasoning capabilities, enabling models to outline steps before execution and provide transparent reasoning paths. This enhancement has reduced errors in…

Despite their impressive capabilities, Large Language Models (LLMs) exhibit unwanted uncertainty, a phenomenon where a model changes a previously correct answer into an incorrect one when re-prompted. This behavior undermines trust and…