Related papers: LM Transparency Tool: Interactive Tool for Analyzi…

Tool-calling is essential for Large Language Model (LLM) agents to complete real-world tasks. While most existing benchmarks assume simple, perfectly documented tools, real-world tools (e.g., general "search" APIs) are often opaque, lacking…

Recent advances in large language models (LLMs) have led to the development of AI-powered tutoring systems that provide interactive support via dialogue. To enable these tutoring systems to provide personalized support, it is essential to…

Large Language Models (LLMs) exhibit remarkable capabilities across a spectrum of tasks in financial services, including report generation, chatbots, sentiment analysis, regulatory compliance, investment advisory, financial knowledge…

Machine learning (ML) is believed to be an effective and efficient tool to build reliable prediction model or extract useful structure from an avalanche of data. However, ML is also criticized by its difficulty in interpretation and…

Locating and editing knowledge in large language models (LLMs) is crucial for enhancing their accuracy, safety, and inference rationale. We introduce ``concept editing'', an innovative variation of knowledge editing that uncovers…

Interpretability tools that offer explanations in the form of a dialogue have demonstrated their efficacy in enhancing users' understanding (Slack et al., 2023; Shen et al., 2023), as one-off explanations may fall short in providing…

Large Language Models (LLMs) have played a pivotal role in advancing Artificial Intelligence (AI). However, despite their achievements, LLMs often struggle to explain their decision-making processes, making them a 'black box' and presenting…

While Large Language Models (LLMs) have achieved strong performance across many NLP tasks, their opaque internal mechanisms hinder trustworthiness and safe deployment. Existing surveys in explainable AI largely focus on post-hoc explanation…

Machine learning (ML) interpretability techniques can reveal undesirable patterns in data that models exploit to make predictions--potentially causing harms once deployed. However, how to take action to address these patterns is not always…

Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…

Mechanistic interpretability seeks to understand how Large Language Models (LLMs) represent and process information. Recent approaches based on dictionary learning and transcoders enable representing model computation in terms of sparse,…

Transformer language models are state of the art in a multitude of NLP tasks. Despite these successes, their opaqueness remains problematic. Recent methods aiming to provide interpretability and explainability to black-box models primarily…

Large language models (LLMs) are becoming increasingly capable, but the mechanisms of their thinking and decision-making processes remain unclear. Chain-of-thoughts (CoTs) have been commonly utilized to externalize LLMs' thinking, but this…

Large Language Models such as GPTs (Generative Pre-trained Transformers) exhibit remarkable capabilities across a broad spectrum of applications. Nevertheless, due to their intrinsic complexity, these models present substantial challenges…

We present LLM-KT, a flexible framework designed to enhance collaborative filtering (CF) models by seamlessly integrating LLM (Large Language Model)-generated features. Unlike existing methods that rely on passing LLM-generated features as…

Language Models (LMs) have significantly advanced natural language processing and enabled remarkable progress across diverse domains, yet their black-box nature raises critical concerns about the interpretability of their internal…

Conversational LLMs function as black box systems, leaving users guessing about why they see the output they do. This lack of transparency is potentially problematic, especially given concerns around bias and truthfulness. To address this…

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

While state-of-the-art language models (LMs) surpass the vast majority of humans in certain domains, their reasoning remains largely opaque, undermining trust in their output. Furthermore, while autoregressive LMs can output explicit…

As large language models (LLMs) continue to advance, there is a growing urgency to enhance the interpretability of their internal knowledge mechanisms. Consequently, many interpretation methods have emerged, aiming to unravel the knowledge…