Related papers: Data-driven Circuit Discovery for Interpretability…
As Large Language Models (LLMs) become increasingly integrated into our daily lives, the potential harms from deceptive behavior underlie the need for faithfully interpreting their decision-making. While traditional probing methods have…
Causal discovery has been widely studied, yet many existing methods rely on strong assumptions or fall into two extremes: either depending on costly interventional signals or partial ground truth as strong priors, or adopting purely data…
Causal discovery seeks to uncover causal relations from data, typically represented as causal graphs, and is essential for predicting the effects of interventions. While expert knowledge is required to construct principled causal graphs,…
Data-driven intelligent computational design (DICD) is a research hotspot emerged under the context of fast-developing artificial intelligence. It emphasizes on utilizing deep learning algorithms to extract and represent the design features…
Reasoning tasks are crucial in many domains, especially in science and engineering. Although large language models (LLMs) have made progress in reasoning tasks using techniques such as chain-of-thought and least-to-most prompting, these…
The cognitive sciences aim to understand intelligence by formalizing underlying operations as computational models. Traditionally, this follows a cycle of discovery where researchers develop paradigms, collect data, and test predefined…
Most existing causal discovery methods rely on the assumption of no latent confounders, limiting their applicability in solving real-life problems. In this paper, we introduce a novel, versatile framework for causal discovery that…
The integration of extensive, dynamic knowledge into Large Language Models (LLMs) remains a significant challenge due to the inherent entanglement of factual data and reasoning patterns. Existing solutions, ranging from non-parametric…
Data discovery - retrieving relevant tables from a data lake in response to user queries - is a fundamental building block for downstream analytics. In practice, data discovery must support different query modalities, including natural…
Structural causal models postulate noisy functional relations among a set of interacting variables. The causal structure underlying each such model is naturally represented by a directed graph whose edges indicate for each variable which…
Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly how to structurally embed acquired knowledge in their neural…
This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on…
Recent work in mechanistic interpretability has shown that behaviors in language models can be successfully reverse-engineered through circuit analysis. A common criticism, however, is that each circuit is task-specific, and thus such…
Lexical Semantic Change Detection (LSCD) is a complex, lemma-level task, which is usually operationalized based on two subsequently applied usage-level tasks: First, Word-in-Context (WiC) labels are derived for pairs of usages. Then, these…
Scaling laws have allowed Pre-trained Language Models (PLMs) into the field of causal reasoning. Causal reasoning of PLM relies solely on text-based descriptions, in contrast to causal discovery which aims to determine the causal…
Uncovering cause-effect relationships from observational time series is fundamental to understanding complex systems. While many methods infer static causal graphs, real-world systems often exhibit dynamic causality-where relationships…
Full integration of robots into real-life applications necessitates their ability to interpret and execute natural language directives from untrained users. Given the inherent variability in human language, equivalent directives may be…
Lie detection is considered a concern for everyone in their day to day life given its impact on human interactions. Thus, people normally pay attention to both what their interlocutors are saying and also to their visual appearances,…
An acyclic causal structure can be described with directed acyclic graph (DAG), where arrows indicate the possibility of direct causation. The task of learning this structure from data is known as "causal discovery." Diverse populations or…
Applying dynamic logics to program verifications is a challenge, because their axiomatic rules for regular expressions can be difficult to be adapted to different program models. We present a novel dynamic logic, called DLp, which supports…