相关论文: Large Language Models can Strategically Deceive th…

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…

The recent release of very large language models such as PaLM and GPT-4 has made an unprecedented impact in the popular media and public consciousness, giving rise to a mixture of excitement and fear as to their capabilities and potential…

When engaging in conversations, dialogue agents in a virtual simulation environment may exhibit their own emotional states that are unrelated to the immediate conversational context, a phenomenon known as self-emotion. This study explores…

We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its behavior out of training. First, we give Claude 3 Opus a system…

Large language models (LLMs) increasingly mediate economic and organisational processes, from automated customer support and recruitment to investment advice and policy analysis. These systems are often assumed to embody rational decision…

Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…

Large, pretrained language models infer powerful representations that encode rich semantic and syntactic content, albeit implicitly. In this work we introduce a novel neural language model that enforces, via inductive biases, explicit…

The rapid advancement of large language models, such as the Generative Pre-trained Transformer (GPT) series, has had significant implications across various disciplines. In this study, we investigate the potential of the state-of-the-art…

While large language models (LLMs), such as GPT-3, appear to be robust and general, their reasoning ability is not at a level to compete with the best models trained for specific natural language reasoning problems. In this study, we…

Cognitive biases often shape human decisions. While large language models (LLMs) have been shown to reproduce well-known biases, a more critical question is whether LLMs can predict biases at the individual level and emulate the dynamics of…

Large language models (LLMs) often produce confident yet incorrect answers, which can lead to risky failures in real-world applications. We study whether post-training can make a model's self-assessment explicit: when the model is…

Adversarial information operations can destabilize societies by undermining fair elections, manipulating public opinions on policies, and promoting scams. Despite their widespread occurrence and potential impacts, our understanding of…

Large-scale Pretrained Language Models (LLMs), such as ChatGPT and GPT4, have shown strong abilities in multilingual translations, without being explicitly trained on parallel corpora. It is interesting how the LLMs obtain their ability to…

As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents' ability to produce harmful outputs or follow malicious instructions, it remains unclear how likely…

Detecting misalignment in large language models is challenging because models may learn to conceal misbehavior during training. Standard auditing techniques fall short: black-box methods often cannot distinguish misaligned outputs from…

As the application of Large Language Models (LLMs) spreads across various industries, there are increasing concerns about the potential for their misuse, especially in sensitive areas such as political discourse. Deliberately aligning LLMs…

This paper investigates the strategic decision-making capabilities of three Large Language Models (LLMs): GPT-3.5, GPT-4, and LLaMa-2, within the framework of game theory. Utilizing four canonical two-player games -- Prisoner's Dilemma,…

Large language models (LLMs) tend to follow maliciously crafted instructions to generate deceptive responses, posing safety challenges. How deceptive instructions alter the internal representations of LLM compared to truthful ones remains…

Large language models have recently demonstrated their exceptional capabilities in supporting and automating various tasks. Among the tasks worth exploring for testing large language model capabilities, we considered data preparation, a…

Today's large language models (LLMs) are trained to align with user preferences through methods such as reinforcement learning. Yet models are beginning to be deployed not merely to satisfy users, but also to generate revenue for the…