Cover Image

Concept-Level Explainability for Auditing & Steering LLM Responses

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Amara, Kenza, Sevastjanova, Rita, El-Assady, Mennatallah
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Challenges and Opportunities in Text Generation Explainability
by: Amara, Kenza, et al.
Published: (2024)

SyntaxShap: Syntax-aware Explainability Method for Text Generation
by: Amara, Kenza, et al.
Published: (2024)

PleaSQLarify: Visual Pragmatic Repair for Natural Language Database Querying
by: Chan, Robin Shing Moon, et al.
Published: (2026)

TopoAlign: Topology-Aware Visual Representation Alignment
by: Yan, Xinyuan, et al.
Published: (2026)

LayerFlow: Layer-wise Exploration of LLM Embeddings using Uncertainty-aware Interlinked Projections
by: Sevastjanova, Rita, et al.
Published: (2025)

Why context matters in VQA and Reasoning: Semantic interventions for VLM input modalities
by: Amara, Kenza, et al.
Published: (2024)

Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agents
by: Ni, Wanchun, et al.
Published: (2026)

Deconstructing Human-AI Collaboration: Agency, Interaction, and Adaptation
by: Holter, Steffen, et al.
Published: (2024)

LayerFlow: Layer‐wise Exploration of LLM Embeddings using Uncertainty‐aware Interlinked Projections
by: Rita Sevastjanova, et al.
Published: (2025)

Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents
by: Yan, Xinyuan, et al.
Published: (2025)

DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition
by: Shi, Danqing, et al.
Published: (2025)

Dia-Lingle: A Gamified Interface for Dialectal Data Collection
by: Sun, Jiugeng, et al.
Published: (2025)

RepIt: Steering Language Models with Concept-Specific Refusal Vectors
by: Siu, Vincent, et al.
Published: (2025)

Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis
by: Cheng, Furui, et al.
Published: (2024)

EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
by: Xu, Haolei, et al.
Published: (2025)

Steering LLM Thinking with Budget Guidance
by: Li, Junyan, et al.
Published: (2025)

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
by: Zhao, Haiyan, et al.
Published: (2025)

Steering Language Models Before They Speak: Logit-Level Interventions
by: An, Hyeseon, et al.
Published: (2026)

Steer Like the LLM: Activation Steering that Mimics Prompting
by: Heyman, Geert, et al.
Published: (2026)

generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation
by: Spinner, Thilo, et al.
Published: (2024)

Output Scouting: Auditing Large Language Models for Catastrophic Responses
by: Bell, Andrew, et al.
Published: (2024)

Reward Learning from Multiple Feedback Types
by: Metz, Yannick, et al.
Published: (2025)

Improving LLM Reasoning through Interpretable Role-Playing Steering
by: Wang, Anyi, et al.
Published: (2025)

A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities
by: Chen, Jiaqi, et al.
Published: (2026)

Critical-Questions-of-Thought: Steering LLM reasoning with Argumentative Querying
by: Castagna, Federico, et al.
Published: (2024)

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering
by: Fang, Yi, et al.
Published: (2026)

When Wording Steers the Evaluation: Framing Bias in LLM judges
by: Hwang, Yerin, et al.
Published: (2026)

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
by: Casademunt, Helena, et al.
Published: (2025)

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
by: Kang, Diancheng, et al.
Published: (2026)

Effectively Steer LLM To Follow Preference via Building Confident Directions
by: Song, Bingqing, et al.
Published: (2025)

Equal Access, Unequal Interaction: A Counterfactual Audit of LLM Fairness
by: Amiri-Margavi, Alireza, et al.
Published: (2026)

RELIC: Investigating Large Language Model Responses using Self-Consistency
by: Cheng, Furui, et al.
Published: (2023)

Steer LLM Latents for Hallucination Detection
by: Park, Seongheon, et al.
Published: (2025)

Toward Subtrait-Level Model Explainability in Automated Writing Evaluation
by: Andrade-Lotero, Alejandro, et al.
Published: (2025)

MIRA: A Bilingual Benchmark for Medical Information Response Audit
by: Xu, Mengyu, et al.
Published: (2026)

Explainability-Based Token Replacement on LLM-Generated Text
by: Mohammadi, Hadi, et al.
Published: (2025)

Steering Awareness: Detecting Activation Steering from Within
by: Rivera, Joshua Fonseca, et al.
Published: (2025)

SEval-Ex: A Statement-Level Framework for Explainable Summarization Evaluation
by: Herserant, Tanguy, et al.
Published: (2025)

VACP: Visual Analytics Context Protocol
by: Stähle, Tobias, et al.
Published: (2026)

Understanding and Mitigating Dataset Corruption in LLM Steering
by: Anderson, Cullen, et al.
Published: (2026)