相关论文: CausalGym: Benchmarking causal interpretability me…

Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substantial ambiguity across language-conditioned tasks, severely…

Interpretability research on large language models (LLMs) has yielded important insights into model behaviour, yet recurring pitfalls persist: findings that do not generalise, and causal interpretations that outrun the evidence. Our…

While pre-trained language models (LMs) have brought great improvements in many NLP tasks, there is increasing attention to explore capabilities of LMs and interpret their predictions. However, existing works usually focus only on a certain…

Objective: This study investigates the potential of Large Language Models (LLMs) as an alternative to human expert elicitation for extracting structured causal knowledge and facilitating causal modeling in biometric and healthcare…

Large language models (LLMs) have mastered abundant simple and explicit commonsense knowledge through pre-training, enabling them to achieve human-like performance in simple commonsense reasoning. Nevertheless, LLMs struggle to reason with…

In this paper, we consider the process of transforming causal domain knowledge into a representation that aligns more closely with guidelines from causal data science. To this end, we introduce two novel tasks related to distilling causal…

Causal discovery aims to estimate causal structures among variables based on observational data. Large Language Models (LLMs) offer a fresh perspective to tackle the causal discovery problem by reasoning on the metadata associated with…

Causal learning has long concerned itself with the accurate recovery of underlying causal mechanisms. Such causal modelling enables better explanations of out-of-distribution data. Prior works on causal learning assume that the high-level…

The ease and speed of spreading misinformation and propaganda on the Web motivate the need to develop trustworthy technology for detecting fallacies in natural language arguments. However, state-of-the-art language modeling methods exhibit…

The instrumental variables (IVs) method is a leading empirical strategy for causal inference. Finding IVs is a heuristic and creative process, and justifying its validity -- especially exclusion restrictions -- is largely rhetorical. We…

The combination of Large Language Models (LLMs), systematic evaluation, and evolutionary algorithms has enabled breakthroughs in combinatorial optimization and scientific discovery. We propose to extend this powerful combination to the…

The development of highly fluent large language models (LLMs) has prompted increased interest in assessing their reasoning and problem-solving capabilities. We investigate whether several LLMs can solve a classic type of deductive reasoning…

Behavioral simulation is increasingly used to anticipate responses to interventions. Large language models (LLMs) enable researchers to specify population characteristics and intervention context in natural language, but it remains unclear…

Most neural models of causality assume static causal graphs, failing to capture the dynamic and sparse nature of physical interactions where causal relationships emerge and dissolve over time. We introduce the Causal Process Framework and…

In this paper, we examine the collaborative dynamics between humans and language models (LMs), where the interactions typically involve LMs proposing text segments and humans editing or responding to these proposals. Productive engagement…

Understanding biases and stereotypes encoded in the weights of Large Language Models (LLMs) is crucial for developing effective mitigation strategies. However, biased behaviour is often subtle and non-trivial to isolate, even when…

Drawing causal conclusions from observational real-world data is a very much desired but challenging task. In this paper we present mixed-method analyses to investigate causal influences of publication trends and behavior on the adoption,…

Causal discovery is becoming a key part in medical AI research. These methods can enhance healthcare by identifying causal links between biomarkers, demographics, treatments and outcomes. They can aid medical professionals in choosing more…

Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…

We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence - their unconscious understanding of linguistic phenomena. Specifically, we use classifier-based probing to examine LMs' internal…