相关论文: Do we really need the Anthropic Principle?

As large language models (LLMs) increasingly participate in high-stakes decision-making, a central societal debate has revolved around which moral frameworks-deontological or utilitarian-should guide machine behavior. However, a largely…

Essentialist beliefs (i.e., believing that members of the same group are fundamentally alike) play a central role in social stereotypes and can lead to harm when left unchallenged. In our work, we conduct exploratory studies into the task…

Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerable to novel attack vectors and distributional shifts. We…

The humanlike responses of large language models (LLMs) have prompted social scientists to investigate whether LLMs can be used to simulate human participants in experiments, opinion polls and surveys. Of central interest in this line of…

As large language models (LLMs) become increasingly integrated into society, their alignment with human morals is crucial. To better understand this alignment, we created a large corpus of human- and LLM-generated responses to various moral…

Large language models (LLMs) increasingly operate in environments where they encounter social information such as other agents' answers, tool outputs, or human recommendations. In humans, such inputs influence judgments in ways that depend…

Recent work in natural language processing (NLP) has focused on ethical challenges such as understanding and mitigating bias in data and algorithms; identifying objectionable content like hate speech, stereotypes and offensive language; and…

I suggest that a "scientific reticence" is inhibiting communication of a threat of potentially large sea level rise. Delay is dangerous because of system inertias that could create a situation with future sea level changes out of our…

This work is intended as a voice in the discussion over previous claims that a pretrained large language model (LLM) based on the Transformer model architecture can be sentient. Such claims have been made concerning the LaMDA model and also…

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), a recent advance in deep learning and machine intelligence, have manifested astonishing capacities, now considered among the most promising for artificial general intelligence. With human-like capabilities,…

We propose a discrete model for how opinion about a given phenomenon, about which various groups of a population have different degrees of enthusiasm, such as fanaticism and extreme social and political positions, including terrorism, may…

Advances in the performance of large language models (LLMs) have led some researchers to propose the emergence of theory of mind (ToM) in artificial intelligence (AI). LLMs can attribute beliefs, desires, intentions, and emotions, and they…

Large language models (LLMs) can generate persuasive narratives at scale, raising concerns about their potential use in disinformation campaigns. Assessing this risk ultimately requires understanding how readers receive such content. In…

Use of artificial intelligence is growing and expanding into applications that impact people's lives. People trust their technology without really understanding it or its limitations. There is the potential for harm and we are already…

Could an AI have conscious experiences? Any answer to this question should conform to Evidentialism - that is, it should be based not on intuition, dogma or speculation but on solid scientific evidence. I argue that such evidence is hard to…

Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations. We define generic personas to represent demographic groups, such as…

LLMs offer valuable capabilities, yet they can be utilized by malicious users to disseminate deceptive information and generate fake news. The growing prevalence of LLMs poses difficulties in crafting detection approaches that remain…

Sentiment analysis in low-resource, culturally nuanced contexts challenges conventional NLP approaches that assume fixed labels and universal affective expressions. We present a diagnostic framework that treats sentiment as a…

Large Language Models (LLMs) are usually aligned with "human values/preferences" to prevent harmful output. Discussions around the alignment of Large Language Models (LLMs) generally focus on preventing harmful outputs. However, in this…