相关论文: Imperative Interference: Social Register Shapes In…

Large language models should follow hierarchical instructions where system prompts override user inputs, yet recent work shows they often ignore this rule while strongly obeying social cues such as authority or consensus. We extend these…

The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI…

The ability to communicate with robots using natural language is a significant step forward in human-robot interaction. However, accurately translating verbal commands into physical actions is promising, but still presents challenges.…

The literature on how large language models handle conflict between their training knowledge and a contradicting document presents a persistent empirical contradiction: some studies find models stubbornly retain their trained answers,…

Several algorithms implemented by language models have recently been successfully reversed-engineered. However, these findings have been concentrated on specific tasks and models, leaving it unclear how universal circuits are across…

In perpetrator treatment, a recurring observation is the dissociation between insight and action: offenders articulate remorse yet behavioral change does not follow. We report four preregistered studies (1,584 multi-agent simulations across…

The conformity bias exhibited by large language models (LLMs) can pose a significant challenge to decision-making in LLM-based multi-agent systems (LLM-MAS). While many prior studies have treated "conformity" simply as a matter of opinion…

The rapid growth of the large language model (LLM) ecosystem raises a critical question: are seemingly diverse models truly independent? Shared pretraining data, distillation, and alignment pipelines can induce hidden behavioral…

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across…

Large natural language models (such as GPT-3 or T5) demonstrate impressive abilities across a range of general NLP tasks. Here, we show that the knowledge embedded in such models provides a useful inductive bias, not just on traditional NLP…

In leading morpho-phonological theories and state-of-the-art text-to-speech systems it is assumed that word pronunciation cannot be learned or performed without in-between analyses at several abstraction levels (e.g., morphological,…

This article introduces the concept of the algorithmic unconscious to designate the set of structural determinations that operate within large language models (LLMs) without being accessible either to the model's own reflexivity or to that…

Do We Need Role Models? How do Role Models Shape Collective Morality? To explore the questions, we build a multi-agent simulation powered by a Large Language Model, where agents with diverse intrinsic drives, ranging from cooperative to…

Natural language is perhaps the most flexible and intuitive way for humans to communicate tasks to a robot. Prior work in imitation learning typically requires each task be specified with a task id or goal image -- something that is often…

We explore unconstrained natural language feedback as a learning signal for artificial agents. Humans use rich and varied language to teach, yet most prior work on interactive learning from language assumes a particular form of input (e.g.,…

Many assignment systems require applicants to rank multi-attribute bundles (e.g., programs combining institution, major, and tuition). We study whether this reporting task is inherently difficult and how reporting interfaces affect accuracy…

Large pre-trained language models such as BERT have been widely used as a framework for natural language understanding (NLU) tasks. However, recent findings have revealed that pre-trained language models are insensitive to word order. The…

Language models can store vast factual knowledge, yet their ability to flexibly use this knowledge for downstream tasks (e.g., via instruction finetuning) remains questionable. This paper investigates four fundamental knowledge manipulation…

Large language models (LLMs) increasingly serve as reasoners and automated evaluators, yet they remain susceptible to cognitive biases -- often altering their reasoning when faced with spurious prompt-level cues such as consensus claims or…

Warning: this paper contains content that may be offensive or upsetting. Language has the power to reinforce stereotypes and project social biases onto others. At the core of the challenge is that it is rarely what is stated explicitly, but…