English
Related papers

Related papers: Measuring Uncertainty in Transformer Circuits with…

200 papers

Symbolic regression (SR) traditionally balances accuracy and complexity, implicitly assuming that simpler formulas are structurally more rational. We argue that this assumption is insufficient: existing algorithms often exploit this metric…

Machine Learning · Computer Science 2026-02-03 Zihan Yu , Guanren Wang , Jingtao Ding , Huandong Wang , Yong Li

In this work, we introduce Entropy Area Score (EAS), a simple yet effective metric to quantify uncertainty in the answer generation process of reasoning large language models (LLMs). EAS requires neither external models nor repeated…

Artificial Intelligence · Computer Science 2025-08-29 Yongfu Zhu , Lin Sun , Guangxiang Zhao , Weihong Lin , Xiangzheng Zhang

Mechanistic Interpretability (MI) aims to reverse-engineer model behaviors by identifying functional sub-networks. Yet, the scientific validity of these findings depends on their stability. In this work, we argue that circuit discovery is…

Machine Learning · Computer Science 2026-02-04 Maxime Méloux , François Portet , Maxime Peyrard

Every mechanistic circuit carries an invisible asterisk: it reflects not just the model's computation, but the analyst's choice of pruning threshold. Change that choice and the circuit changes, yet current practice treats a single pruned…

Computation and Language · Computer Science 2026-03-23 Swapnil Parekh

Automated Essay Scoring (AES) systems now reach near human agreement on some public benchmarks, yet real-world adoption, especially in high-stakes examinations, remains limited. A principal obstacle is that most models output a single score…

Computation and Language · Computer Science 2025-09-22 Ahmed Karim , Qiao Wang , Zheng Yuan

Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pursues this goal by identifying circuits - minimal subnetworks responsible for specific…

Artificial Intelligence · Computer Science 2026-03-03 Alaa Anani , Tobias Lorenz , Bernt Schiele , Mario Fritz , Jonas Fischer

Entropy-based confidence signals are increasingly leveraged to improve reasoning in large language models (LLMs), yet existing approaches treat confidence as a static quantity -- typically aggregated over tokens. We show that the…

Machine Learning · Computer Science 2026-03-09 Chenghua Zhu , Siyan Wu , Xiangkang Zeng , Zishan Xu , Zhaolu Kang , Yifu Guo , Yuquan Lu , Junduan Huang , Guojing Zhou

Evaluating whether explanations faithfully reflect a model's reasoning remains an open problem. Existing benchmarks use single interventions without statistical testing, making it impossible to distinguish genuine faithfulness from…

Computation and Language · Computer Science 2026-03-20 Abhinaba Basu , Pavan Chakraborty

Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities, entropy, and self-consistency can become brittle under calibration--deployment…

Computation and Language · Computer Science 2026-04-20 Yanli Wang , Peng Kuang , Xiaoyu Han , Kaidi Xu , Haohan Wang

Deep learning models perform best with abundant, high-quality labels, yet such conditions are rarely achievable in EEG-based emotion recognition. Electroencephalogram (EEG) signals are easily corrupted by artifacts and individual…

Machine Learning · Computer Science 2025-11-20 Hyo-Jeong Jang , Hye-Bin Shin , Kang Yin

Electrochemical Impedance Spectroscopy (EIS) is a crucial technique for assessing corrosion of a metallic materials. The analysis of EIS hinges on the selection of an appropriate equivalent circuit model (ECM) that accurately characterizes…

In this paper, we introduce the Interpretable Cross-Examination Technique (ICE-T), a novel approach that leverages structured multi-prompt techniques with Large Language Models (LLMs) to improve classification performance over zero-shot and…

Computation and Language · Computer Science 2024-05-14 Goran Muric , Ben Delay , Steven Minton

Analysis of Electrochemical Impedance Spectroscopy (EIS) data for electrochemical systems often consists of defining an Equivalent Circuit Model (ECM) using expert knowledge and then optimizing the model parameters to deconvolute various…

Large language models (LLMs) have demonstrated remarkable capabilities in generating programs from natural language descriptions, yet ensuring their correctness without an external oracle remains a critical challenge. To solve the…

Software Engineering · Computer Science 2026-04-07 Yunxiang Wei , Tianlin Li , Yuwei Zheng , Yanni Dong , Aishan Liu , Qiang Hu , Xiaoyu Zhang , Mingfei Cheng , Jian Yang

Large Language Models (LLMs) excel on many task-specific benchmarks, yet the mechanisms that drive this success remain poorly understood. We move from asking what these systems can do to asking how they process information. Our contribution…

Artificial Intelligence · Computer Science 2026-02-04 Jae Wan Shim

Context engineering for large language model (LLM) agents requires distinguishing pragmatically useful information from misleading distractors. We introduce Entropic Context Shaping (ECS), an information-theoretic framework that measures…

Computation and Language · Computer Science 2026-01-21 Hyunjun Kim

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

Computation and Language · Computer Science 2026-03-12 Ajay Pravin Mahale

Understanding the decision-making processes of large language models (LLMs) is essential for their trustworthy development and deployment. However, current interpretability methods often face challenges such as low resolution and high…

Computation and Language · Computer Science 2025-10-14 Tian Lan , Jinyuan Xu , Xue He , Jenq-Neng Hwang , Lei Li

Mechanistic interpretability produces circuit-level causal analyses of neural network behaviour, but discovered circuits often remain isolated experimental artefacts: there is no shared formal representation for what circuits compute, how…

Machine Learning · Computer Science 2026-05-21 Nura Aljaafari , Danilo S. Carvalho , Andre Freitas

The circuits framework in mechanistic interpretability aims to identify causally important sparse subgraphs of model components, typically evaluated by measuring necessity and sufficiency. We measure circuit reuse, the proportion of…

Computation and Language · Computer Science 2026-05-12 Michael Li , Nishant Subramani
‹ Prev 1 2 3 10 Next ›