相关论文: Learning a Structural Causal Model for Intuition R…

We introduce CausaLab, a scalable environment for evaluating interactive causal discovery by LLM agents. Unlike prior evaluations, CausaLab evaluates both whether an agent can solve a problem using causal evidence and whether its answer is…

People in conversation entrain their linguistic behaviours through spontaneous alignment mechanisms [7] - both in face-to-face and computer-mediated communication (CMC) [8]. In CMC, one of the mechanisms through which linguistic entrainment…

The causal capabilities of large language models (LLMs) are a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy. We conduct a "behavorial"…

The problem of explaining the results produced by machine learning methods continues to attract attention. Neural network (NN) models, along with gradient boosting machines, are expected to be utilized even in tabular data with high…

Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents. However, this problem has not been studied in large-scale conversation generation so far. In this paper, we propose Emotional…

Effective evaluation methods remain a significant challenge for research on open-domain conversational dialogue systems. Explicit satisfaction ratings can be elicited from users, but users often do not provide ratings when asked, and those…

Recent advances in large language models (LLMs) have popularized the chain-of-thought (CoT) paradigm, in which models produce explicit reasoning steps in natural language. Although this approach improves interpretability and facilitates…

This paper introduces a causal attribution model to enhance the interpretability of large language models (LLMs) and improve their causal reasoning abilities via precise fine-tuning. Despite LLMs' proficiency in diverse tasks, their…

Mathematical reasoning in large language models (LMs) has garnered significant attention in recent work, but there is a limited understanding of how these models process and store information related to arithmetic tasks within their…

Recent papers show LLMs achieve near-random accuracy in causal relation classification, raising questions about whether such failures arise from limited pretraining exposure or deeper representational gaps. We investigate this under…

This paper presents a novel latent variable recurrent neural network architecture for jointly modeling sequences of words and (possibly latent) discourse relations between adjacent sentences. A recurrent neural network generates individual…

Precisely understanding users' contextual search intent has been an important challenge for conversational search. As conversational search sessions are much more diverse and long-tailed, existing methods trained on limited data still show…

Causal discovery, the problem of inferring the direction of causality, is generally ill-posed. We use the language of structural causal models (SCM) to show that assuming that the causal relations are acyclic and invariant across multiple…

While LLMs exhibit impressive fluency and factual recall, they struggle with robust causal reasoning, often relying on spurious correlations and brittle patterns. Similarly, traditional Reinforcement Learning agents also lack causal…

Natural language communication is an intricate and complex process. The speaker usually begins with an intention and motivation of what is to be communicated, and what effects are expected from the communication, while taking into…

Unlike human reasoning in abstract conceptual spaces, large language models (LLMs) typically reason by generating discrete tokens, which potentially limit their expressive power. The recent work Soft Thinking has shown that LLMs' latent…

Causality understanding between events is a critical natural language processing task that is helpful in many areas, including health care, business risk management and finance. On close examination, one can find a huge amount of textual…

Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought. These longer intermediate reasoning…

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…

Consider the finite state graph that results from a simple, discrete, dynamical system in which an agent moves in a rectangular grid picking up and dropping packages. Can the state variables of the problem, namely, the agent location and…