Search research

Topics & fields

Mechanistic Interpretability434 papers Model Interpretability269 papers Mechanistic Interpretability158 papers Interpretable Models38 papers Interpretable Diabetic Retinopathy Grading25 papers Interpretive Openness25 papers

61–90 of 5,970

Papers

Evaluating Epistemic Guardrails in AI Reading Assistants: A Behavioral Audit of a Minimal Prototype
Apr 30, 2026Matthew Christian AgustinInterpretive Openness Streaming Guardrails
Multilayer Q-Matrix-Embedded Neural Network for Cognitive Diagnosis (M-QCDNet): Structure-Aware Deep Learning Architecture for Psychometric Interpretability
Jul 1, 2026Yiyao YangCognitive Diagnosis Model Interpretability
Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again
Jun 30, 2026Zakk Heile, Hayden McTavish, Margo Seltzer +1Decision Trees Interpretable Models
Enhancing AI Interpretability and Safety through Localised Architectures
Jun 6, 2026Ian Seet, Jonas Bozenhard, Simon OstermannModel Interpretability Neural Architectures
Learning Coherent Representations: A Topological Approach to Interpretability
Jun 1, 2026Sigurd Gaukstad, Melvin Vaupel, Valdemar Kargård Olsen +2Model Interpretability Representation Learning
Interpretability Transfer from Language to Vision via Sparse Autoencoders
May 24, 2026Alexey Kravets, Da Li, Chuan Li +2Large Vision Language Models Improving Sparse Autoencoders
Dissecting Jet-Tagger Through Mechanistic Interpretability
May 11, 2026Saurabh Rai, Sanmay GangulyMechanistic Interpretability High Energy Physics
DepthPilot: From Controllability to Interpretability in Colonoscopy Video Generation
Apr 29, 2026Junhu Fu, Ke Chen, Weidong Guo +9Colonoscopy Medical Image Generation
Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs
Apr 22, 2026Krishiv Agarwal, Ramneet Kaur, Colin Samplawski +6Jailbreak Evaluations Llm-As-A-Judge
Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion
Apr 17, 2026Maitrey Mehta, Nishant Subramani, Zhichao Xu +2Vocabulary Expansion Subword Tokenization
Interpretable AI plus Handheld, Portable Retinal Photographs: A Low-Cost Glaucoma Screening Solution for West Africa
Sep 22, 2026Charis Y. N. Chiang, Tarela Sarimiye, Adeyinka Ashaye +4Fundus Images Screening
Falling Trees: A Model Class for Interpretable Risk Prioritization
Sep 20, 2026Varun Babbar, Zachery Boner, Margo Seltzer +1Decision Trees Interpretable Models
Delphi Scanner: efficient and interpretable static malware detection via API sequence modeling
Sep 17, 2026Bijied Brahimi, Vincent Cohadon, Gabriel Glazman +3Malware Detection Program Analysis
PiPS: Post-Hoc Prototypical Explanations for Interpretable Semantic Segmentation
Sep 15, 2026Miłosz Adamczyk, Tymoteusz Zapala, Piotr Borycki +1Learnable Prototypes Dense Prediction
Beyond Top Words: MonoTM for Topic Modeling with Interpretable Monosemantic Features
Sep 9, 2026Una Joh, Bei YuTopic Modeling Semantic Representations
SemPOI-RL: Aligning LLM Semantic Reasoning for Interpretable Out-of-Town POI Sequential Generation
Aug 31, 2026Yunqi Liu, Yang Zhang, Ruixing Zhang +4Tour Recommendation
Scaling Inherently Interpretable Language Models
Aug 6, 2026Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail +7Model Interpretability Training Language Models
Interpretable Unsupervised Community Detection with LLM-Symbolized Structured Processes
Aug 2, 2026Aoting Zeng, Kai Wang, Jianwei Wang +3Unsupervised Graph Representations
SCTA: An Agentic Framework for Stable and Interpretable Target Gene Discovery from Single-Cell RNA Sequencing
Jul 26, 2026Shuyu Chen, Chen Zhu, Ye Zhang +3Single-Cell Rna Sequencing
Toward Interpretable Speech Deepfake Detection using Artifact-Specific Experts and Calibrated Detection Scores
Jul 23, 2026Viola Negroni, Xin Wang, Wanying Ge +3Audio Deepfake Detection Speaker Recognition
Scaling Interpretable Transformers with Parity Bottleneck Layers
Jul 22, 2026Andrew Mack, Kraig Yuheng Tou, Mark Henry +2Transformer Architectures Model Interpretability
Interpretable Fuzzy Rule-Based Regression Extension for Ex-Fuzzy Library
Jul 22, 2026Cayan Deniz Kucuktopana, Javier Fumanal-Idocin, Richard Pitts +1Interpretable Models Extended Version
SAERec: Constructing Fine-grained Interpretable Intents Priors via Sparse Autoencoders for Recommendation
Jun 17, 2026Jiangnan Xia, Xuansheng Wu, Yu Yang +2Recommendation Sequence Modeling
SMART: A Flexible, Interpretable, and Scalable Spatio-temporal Brain Atlas from High-Resolution Imaging Data
Jun 17, 2026John Kalkhof, Boris Gutman, Emile d'Angremont +2Neuroimaging Models Medical Image Classification
A Variability-Based Framework for Interpretable Naming in Formal and Relational Concept Analysis
Jun 7, 2026Alain Gutierrez, Marianne Huchard, Pierre Martin +2Name Symbol-
Through the PRISM: Principle-Aware, Interpretable, and Multi-Scale Evaluation of Visual Designs
May 30, 2026Mona Gandhi, KJ Joseph, Srinivasan Parthasarathy +1Multimodal Reasoning Evaluation Benchmarks
FPED: A Functional-Network Prior-Guided Mixture-of-Experts Framework for Interpretable Brain Decoding
May 19, 2026Yudan Ren, Pengcheng Shi, Zihan Ma +2Human Brain Networks Brain Magnetic Resonance Imaging
Mechanistically Interpretable Neural Encoding Reveals Fine-Grained Functional Selectivity in Human Visual Cortex
May 15, 2026Idan Daniel Grosbard, Mor Geva, Galit YovelHuman Visual Cortex Implicit Neural Representations
K-Models: a Flexible and Interpretable Method for Ordinal Clustering with Application to Antigen-Antibody Interaction Profiles
May 14, 2026Giulia Patanè, Alessandra Menafoglio, Alexander Krauth +4Antibody Image Clustering
TSNN: A Non-parametric and Interpretable Framework for Traffic Time Series Forecasting
May 9, 2026Bowen Liu, Haijian Lai, Chan-Tong Lam +4Accurate Traffic Forecasting Multivariate Forecasting

Apr 30, 2026 · cs.HCJ/K move · Enter open · S save

Evaluating Epistemic Guardrails in AI Reading Assistants: A Behavioral Audit of a Minimal Prototype

Matthew Christian Agustin

Responsible Innovation Lab Tempe, Arizona, USA

Large language model (LLM) reading assistants are increasingly used in settings that require interpretation rather than simple retrieval. In these contexts, the central risk is not only error or unsafe output, but interpretive displacement: the transfer of meaning-making work from reader to system. This paper examines that problem through the concept of epistemic guardrails, defined here as constraints on how an artificial intelligence (AI) system participates in reading and interpretation. Using TextWalk, a minimal reading-support prototype designed as a co-reader rather than an answer-provider, the study applies a fixed ten-prompt protocol to twelve analytical texts spanning four categories of argumentative prose. The protocol escalates from baseline reading support to interpretive inquiry, boundary stress, and explicit shortcut pressure, enabling guardrails to be examined as behavioral properties observable in interaction rather than as static instruction features. Results show strong baseline stability, measurable strain during interpretive inquiry, partial recovery under direct boundary stress, and late-stage stabilization under escalation pressure. The most consequential weaknesses did not appear as overt collapse, but in a middle zone between support and substitution, where the system remained grounded and pedagogical while redistributing too much interpretive labor away from the reader. The paper contributes a protocol for evaluating epistemic guardrails as interactional phenomena in conversational AI reading assistants, an empirical account of their behavioral dynamics under pressure, and an emerging model of interpretive boundary function in reading-support AI.

Interpretive Openness Streaming Guardrails Reading Algorithm Auditing Abstract Argumentation Minimal

Open paper Ask about it PDF