Related papers: New Faithfulness-Centric Interpretability Paradigm…

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…

While current large language models (LLMs) perform well on many knowledge-related tasks, they are limited by relying on their parameters as an implicit storage mechanism. As a result, they struggle with memorizing rare events and with…

The widespread application of pre-trained language models (PLMs) in natural language processing (NLP) has led to increasing concerns about their explainability. Selective rationalization is a self-explanatory framework that selects…

Large language models (LLMs) augmented with retrieval systems have demonstrated significant potential in handling knowledge-intensive tasks. However, these models often struggle with unfaithfulness issues, generating outputs that either…

Natural language explanations in recommender systems are often framed as a review generation task, leveraging user reviews as ground-truth supervision. While convenient, this approach conflates a user's opinion with the system's reasoning,…

Speech foundation models (SFMs) are increasingly hailed as powerful computational models of human speech perception. However, since their representations are inherently black-box, it remains unclear what drives their alignment with brain…

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains…

Although deep models achieve high predictive performance, it is difficult for humans to understand the predictions they made. Explainability is important for real-world applications to justify their reliability. Many example-based…

Recent breakthroughs in NLP research, such as the advent of Transformer models have indisputably contributed to major advancements in several tasks. However, few works research robustness and explainability issues of their evaluation…

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…

Large language models (LLMs) are trained to imitate humans to explain human decisions. However, do LLMs explain themselves? Can they help humans build mental models of how LLMs process different inputs? To answer these questions, we propose…

Although a recent shift has been made in the field of predictive process monitoring to use models from the explainable artificial intelligence field, the evaluation still occurs mainly through performance-based metrics, thus not accounting…

Evaluating faithfulness of Large Language Models (LLMs) to a given task is a complex challenge. We propose two new unsupervised metrics for faithfulness evaluation using insights from information theory and thermodynamics. Our approach…

Foundation models (FMs), including large language models, have become increasingly popular due to their wide-ranging applicability and ability to understand human-like semantics. While previous research has explored the use of FMs in…

Large Language Models (LLMs) are increasingly deployed for clinical reasoning tasks, which inherently require eliciting calibrated probabilistic beliefs based on available evidence. However, real-world clinical data are frequently…

People judge interactions with large language models (LLMs) as successful when outputs match what they want, not what they type. Yet LLMs are trained to predict the next token solely from text input, not underlying intent. Because written…

Text-based explainable recommendation aims to generate natural-language explanations that justify item recommendations, to improve user trust and system transparency. Although recent advances leverage LLMs to produce fluent outputs, a…

Chain-of-Thought (CoT) faithfulness, i.e., whether CoTs genuinely reflect large language models' (LLM) underlying behavior, is typically evaluated under two disjoint paradigms: contextual faithfulness, measured by perturbing the input or…

Massive language models are the core of modern NLP modeling and have been shown to encode impressive amounts of commonsense and factual information. However, that knowledge exists only within the latent parameters of the model, inaccessible…

Rational speakers are supposed to know what they know and what they do not know, and to generate expressions matching the strength of evidence. In contrast, it is still a challenge for current large language models to generate corresponding…