#explainability

try —

7 papers match

cs.CV2026

Explaining Image Similarity with Automatically Extracted Concept Activation Vectors

Isaac Roberts, Petra Bevandic, Alexander Schulz +1

The paper proposes a model‑agnostic method that uses automatically discovered concept activation vectors to explain why two images are considered similar, by perturbing embeddings…

#image similarity#explainability#concept activation vectors#representation learning
cs.AI2026

TraceCoder: Explainable and Auditable Code Generation with Position-Key Snippet Versioning

Rwaida Alssadi, Muntaser Syed, Balaji Kasula +6

The paper introduces TraceCoder, a system that records detailed provenance for each code snippet generated by large language models, visualizes the evolution of code through repair…

#code generation#explainability#auditability#llm-based programming
cs.LG2026

Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks

Xin Xu, Siru Tao, Kaizhen Tan

The paper shows that gradient‑based explainers for graph neural networks can produce arbitrary top‑k edge explanations when the input graph has nontrivial automorphisms, and provid…

#graph neural networks#explainability#graph automorphisms#top‑k explanations
cs.CL2026

Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA

Sushant Gautam, Vajira Thambawita, Michael A. Riegler +2

The paper studies how design choices affect the reliability and interpretability of multimodal visual question answering systems for gastrointestinal endoscopy, finding that struct…

#multimodal vqa#healthcare ai#explainability#data fusion
cs.LG2026

Explaining Temporal Graph Neural Networks via Feature-induced Information Flow

Ping Xiong, Thomas Schnake, Klaus-Robert Müller +1

The paper introduces an attribution method that explains temporal graph neural networks by quantifying information flow through both event embeddings and event-induced variables, i…

#temporal graphs#explainability#graph neural networks#information flow
cs.CL2026

Robust Explanations for User Trust in Enterprise NLP Systems

Guilin Zhang, Kai Zhao, Jeffrey Friedman +3

The paper introduces a black‑box framework to evaluate the robustness of token‑level explanations for enterprise NLP models, measuring how often top explanatory tokens change under…

#explainability#robustness evaluation#black-box models#large language models
cs.IR2026

Explaining When PRF Fails: Participatory Auditing for Selective Query Expansion

Zeyan Liang, Graham McDonald, Iadh Ounis

The paper investigates why pseudo-relevance feedback (PRF) harms many queries and introduces a two‑stage audit‑then‑automate framework that uses user audits and LLM‑based rerankers…

#pseudo-relevance feedback#query drift#explainability#selective retrieval

One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.