Related papers: FADE: Why Bad Descriptions Happen to Good Features

Being able to interpret, or explain, the predictions made by a machine learning model is of fundamental importance. This is especially true when there is interest in deploying data-driven models to make high-stakes decisions, e.g. in…

Machine learning (ML) models are becoming increasingly common in the atmospheric science community with a wide range of applications. To enable users to understand what an ML model has learned, ML explainability has become a field of active…

Automation in software engineering increasingly relies on large language models (LLMs) to generate, review, and assess code artifacts. However, establishing LLMs as reliable evaluators remains an open challenge: human evaluations are…

The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…

Data visualization in the form of charts plays a pivotal role in data analysis, offering critical insights and aiding in informed decision-making. Automatic chart understanding has witnessed significant advancements with the rise of large…

Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related…

The use of large language models (LLMs) in qualitative analysis offers enhanced efficiency but raises questions about their alignment with the contextual nature of research for design (RfD). This research examines the trustworthiness of…

Sparse Autoencoder (SAE) features have become essential tools for mechanistic interpretability research. SAE features are typically characterized by examining their activating examples, which are often "monosemantic" and align with human…

Large language models (LLMs) are increasingly used to support the analysis of complex financial disclosures, yet their reliability, behavioral consistency, and transparency remain insufficiently understood in high-stakes settings. This…

Methods for interpreting machine learning black-box models increase the outcomes' transparency and in turn generates insight into the reliability and fairness of the algorithms. However, the interpretations themselves could contain…

What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the…

Understanding training dynamics and feature evolution is crucial for the mechanistic interpretability of large language models (LLMs). Although sparse autoencoders (SAEs) have been used to identify features within LLMs, a clear picture of…

Large Language Models have significantly advanced natural language processing tasks, but remain prone to generating incorrect or misleading but plausible arguments. This issue, known as hallucination, is particularly concerning in…

Model interpretability is an increasingly important component of practical machine learning. Some of the most common forms of interpretability systems are example-based, local, and global explanations. One of the main challenges in…

Enforcing archival standards requires specialized expertise, and manually creating metadata descriptions for archival materials is a tedious and error-prone task. This work aims at exploring the potential of agentic AI and large language…

Automatic image anomaly detection is important for quality inspection in the manufacturing industry. The usual unsupervised anomaly detection approach is to train a model for each object class using a dataset of normal samples. However, a…

Attribution algorithms are essential for enhancing the interpretability and trustworthiness of deep learning models by identifying key features driving model decisions. Existing frameworks, such as InterpretDL and OmniXAI, integrate…

The analysis of DNA sequences has become critical in numerous fields, from evolutionary biology to understanding gene regulation and disease mechanisms. While deep neural networks can achieve remarkable predictive performance, they…

Much of the reported progress in file-level software defect prediction (SDP) is, in reality, nothing but an illusion of accuracy. Over the last decades, machine learning and deep learning models have reported increasing performance across…

Evaluating Large Language Models (LLMs) on repository-level feature implementation is a critical frontier in software engineering. However, establishing a benchmark that faithfully mirrors realistic development scenarios remains a…