相关论文: The Curious Case of Control

Persistent language-model agents increasingly combine tool use, tiered memory, reflective prompting, and runtime adaptation. In such systems, behavior is shaped not only by current prompts but by mutable internal conditions that influence…

Large language models (LLMs) perform well at a myriad of tasks, but explaining the processes behind this performance is a challenge. This paper investigates whether LLMs can give faithful high-level explanations of their own internal…

Both humans and large language models (LLMs) exhibit content effects: biases in which the plausibility of the semantic content of a reasoning problem influences judgments regarding its logical validity. While this phenomenon in humans is…

Transformer-based language models have recently achieved remarkable results in many natural language tasks. However, performance on leaderboards is generally achieved by leveraging massive amounts of training data, and rarely by encoding…

We introduce a class of stochastic models for the dynamics of two linguistic variants that are competing to become the single, shared convention within an unstructured community of speakers. Different instances of the model are…

Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violates privacy (exposing…

Prior research demonstrates that performance of language models on reasoning tasks can be influenced by suggestions, hints and endorsements. However, the influence of endorsement source credibility remains underexplored. We investigate…

This case study investigates the extent to which a language model (GPT-2) is able to capture native speakers' intuitions about implicit causality in a sentence completion task. We first reproduce earlier results (showing lower surprisal…

Both humans and neural language models are able to perform subject-verb number agreement (SVA). In principle, semantics shouldn't interfere with this task, which only requires syntactic knowledge. In this work we test whether meaning…

One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the…

Language models are typically evaluated on their success at predicting the distribution of specific words in specific contexts. Yet linguistic knowledge also encodes relationships between contexts, allowing inferences between word…

Language models generally produce grammatical text, but they are more likely to make errors in certain contexts. Drawing on paradigms from psycholinguistics, we carry out a fine-grained analysis of those errors in different syntactic…

Sequential modelling entails making sense of sequential data, which naturally occurs in a wide array of domains. One example is systems that interact with users, log user actions and behaviour, and make recommendations of items of potential…

There has been a noticeable shift in the relative composition of the industry in the developed countries in recent years; manufacturing is decreasing while the service sector is becoming more important. However, currently most simulation…

Recently, large pre-trained language models (LLMs) have demonstrated superior language understanding abilities, including zero-shot causal reasoning. However, it is unclear to what extent their capabilities are similar to human ones. We…

Multi-step reasoning instruction, such as chain-of-thought prompting, is widely adopted to explore better language models (LMs) performance. We report on the systematic strategy that LMs employ in such a multi-step reasoning process. Our…

Heralding the advent of autonomous vehicles and mobile robots that interact with humans, responsibility in spatial interaction is burgeoning as a research topic. Even though metrics of responsibility tailored to spatial interactions have…

LMs' alignment with human reading behavior (i.e. psychometric predictive power; PPP) is known to improve during pretraining up to a tipping point, beyond which it either plateaus or degrades. Various factors, such as word frequency, recency…

Children's acquisition of filler-gap dependencies has been argued by some to depend on innate grammatical knowledge, while others suggest that the distributional evidence available in child-directed speech suffices. Unfortunately, the…

Do large language models (LLMs) make human-like linguistic generalizations? Dentella et al. (2023) ("DGL") prompt several LLMs ("Is the following sentence grammatically correct in English?") to elicit grammaticality judgments of 80 English…