Copertina

Learning to Explain: Prototype-Based Surrogate Models for LLM Classification

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wei, Bowen, Fazli, Mehrdad, Zhu, Ziwei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Advancing Interpretability in Text Classification through Prototype Learning
di: Wei, Bowen, et al.
Pubblicazione: (2024)

Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
di: Fazli, Mehrdad, et al.
Pubblicazione: (2025)

Context-Aware Decoding for Faithful Vision-Language Generation
di: Fazli, Mehrdad, et al.
Pubblicazione: (2026)

VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models
di: Raj, Chahat, et al.
Pubblicazione: (2025)

Fighting Spurious Correlations in Text Classification via a Causal Learning Perspective
di: Zhou, Yuqing, et al.
Pubblicazione: (2024)

CORTEX: Collaborative LLM Agents for High-Stakes Alert Triage
di: Wei, Bowen, et al.
Pubblicazione: (2025)

Robust Text Classification: Analyzing Prototype-Based Networks
di: Sourati, Zhivar, et al.
Pubblicazione: (2023)

Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models
di: Zhou, Yuqing, et al.
Pubblicazione: (2024)

Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks
di: Wen, Ximing
Pubblicazione: (2024)

Detect, Explain, Escalate: Sustainable Dialogue Breakdown Management for LLM Agents
di: Ghassel, Abdellah, et al.
Pubblicazione: (2025)

Bias Association Discovery Framework for Open-Ended LLM Generations
di: Pan, Jinhao, et al.
Pubblicazione: (2025)

Explaining Length Bias in LLM-Based Preference Evaluations
di: Hu, Zhengyu, et al.
Pubblicazione: (2024)

Rationale-Augmented Retrieval with Constrained LLM Re-Ranking for Task Discovery
di: Wei, Bowen
Pubblicazione: (2025)

Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification
di: Li, Mengyu, et al.
Pubblicazione: (2024)

AnimatedLLM: Explaining LLMs with Interactive Visualizations
di: Kasner, Zdeněk, et al.
Pubblicazione: (2025)

Harnessing LLMs Explanations to Boost Surrogate Models in Tabular Data Classification
di: Shi, Ruxue, et al.
Pubblicazione: (2025)

Prototype-Based Dynamic Steering for Large Language Models
di: Kayan, Ceyhun Efe, et al.
Pubblicazione: (2025)

Computational Law: Datasets, Benchmarks, and Ontologies
di: Küçük, Dilek, et al.
Pubblicazione: (2025)

Exploring Model Editing for LLM-based Aspect-Based Sentiment Classification
di: Li, Shichen, et al.
Pubblicazione: (2025)

Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations
di: Rinki, Mamnuya, et al.
Pubblicazione: (2025)

ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
di: Li, Chaoyu, et al.
Pubblicazione: (2025)

Latent Debate: A Surrogate Framework for Interpreting LLM Thinking
di: Chen, Lihu, et al.
Pubblicazione: (2025)

Token Masking Improves Transformer-Based Text Classification
di: Xu, Xianglong, et al.
Pubblicazione: (2025)

Metadata Conditioned Large Language Models for Localization
di: Mukherjee, Anjishnu, et al.
Pubblicazione: (2026)

Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery
di: Deng, Yimin, et al.
Pubblicazione: (2024)

Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models
di: Farahani, Mehrdad, et al.
Pubblicazione: (2024)

Crossroads of Continents: Automated Artifact Extraction for Cultural Adaptation with Large Multimodal Models
di: Mukherjee, Anjishnu, et al.
Pubblicazione: (2024)

Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions
di: Zhu, Jian-Qiao, et al.
Pubblicazione: (2025)

LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models
di: Zhu, Xi, et al.
Pubblicazione: (2025)

Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs
di: Qin, Yijian, et al.
Pubblicazione: (2023)

NoMatterXAI: Generating "No Matter What" Alterfactual Examples for Explaining Black-Box Text Classification Models
di: Nguyen, Tuc, et al.
Pubblicazione: (2024)

Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text Detection
di: Sun, Ke, et al.
Pubblicazione: (2026)

Enhanced Multimodal Aspect-Based Sentiment Analysis by LLM-Generated Rationales
di: Cao, Jun, et al.
Pubblicazione: (2025)

xTower: A Multilingual LLM for Explaining and Correcting Translation Errors
di: Treviso, Marcos, et al.
Pubblicazione: (2024)

Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models
di: Jiang, Yiwen, et al.
Pubblicazione: (2025)

Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling
di: Feng, Zihao, et al.
Pubblicazione: (2025)

Large Margin Prototypical Network for Few-shot Relation Classification with Fine-grained Features
di: Fan, Miao, et al.
Pubblicazione: (2024)

Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model
di: Miao, Yibo, et al.
Pubblicazione: (2023)

What's Not Said Still Hurts: A Description-Based Evaluation Framework for Measuring Social Bias in LLMs
di: Pan, Jinhao, et al.
Pubblicazione: (2025)

Diagnosis Is Not Prescription: Linguistic Co-Adaptation Explains Patching Hazards in LLM Pipelines
di: Jeonghun, Yoon, et al.
Pubblicazione: (2026)