Cover Image

ICE: Intervention-Consistent Explanation Evaluation with Statistical Grounding for LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Basu, Abhinaba, Chakraborty, Pavan
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning 68T50, 62G10, 62H15 I.2.7; I.2.6; I.5.2; G.3
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration
by: Lin, Shuhang, et al.
Published: (2026)

Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages
by: de Zuazo, Xabier, et al.
Published: (2025)

MEDLEY-BENCH: Scale Buys Evaluation but Not Control in AI Metacognition
by: Abtahi, Farhad, et al.
Published: (2026)

When Does Content-Based Routing Work? Representation Requirements for Selective Attention in Hybrid Sequence Models
by: Basu, Abhinaba
Published: (2026)

Distribution-Free Uncertainty Quantification for Continuous AI Agent Evaluation
by: Gao, Yuxuan, et al.
Published: (2026)

Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness
by: Basu, Abhinaba, et al.
Published: (2026)

Latent-Autoregressive GP-VAE Language Model
by: Ruffenach, Yves
Published: (2025)

Conformal Prediction Sets for Next-Token Prediction in Large Language Models: Balancing Coverage Guarantees with Set Efficiency
by: Kotla, Yoshith Roy, et al.
Published: (2025)

Classifier Calibration at Scale: An Empirical Study of Model-Agnostic Post-Hoc Methods
by: Manokhin, Valery, et al.
Published: (2026)

SCOPE: Selective Conformal Optimized Pairwise LLM Judging
by: Badshah, Sher, et al.
Published: (2026)

ML-driven detection and reduction of ballast information in multi-modal datasets
by: Solovko, Yaroslav
Published: (2026)

Transactional Attention: Semantic Sponsorship for KV-Cache Retention
by: Basu, Abhinaba
Published: (2026)

ValueBlindBench: Agreement-Gated Stress Testing of LLM-Judged Investment Rationales Before Returns Are Observable
by: Chang, Sidi, et al.
Published: (2026)

A Hybrid Framework for Real-Time Data Drift and Anomaly Identification Using Hierarchical Temporal Memory and Statistical Tests
by: Bandyopadhyay, Subhadip, et al.
Published: (2025)

Advancements in Machine Learning and Deep Learning for Early Detection and Management of Mental Health Disorder
by: Kannan, Kamala Devi, et al.
Published: (2024)

Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning
by: Pather, Kaviraj, et al.
Published: (2025)

GIM: Evaluating models via tasks that integrate multiple cognitive domains
by: Patel, Rohit, et al.
Published: (2026)

Can Agentic AI Match the Performance of Human Data Scientists?
by: Luo, An, et al.
Published: (2025)

AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science
by: Luo, An, et al.
Published: (2026)

When Names Change Verdicts: Intervention Consistency Reveals Systematic Bias in LLM Decision-Making
by: Basu, Abhinaba, et al.
Published: (2026)

AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science
by: Luo, An, et al.
Published: (2025)

Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference
by: Du, Jin, et al.
Published: (2025)

Closed-Form Beta Distribution Estimation from Sparse Statistics with Random Forest Implicit Regularization
by: Landers, Jonathan R.
Published: (2025)

ProactBench: Beyond What The User Asked For
by: Harfi, Sepehr, et al.
Published: (2026)

Claim Automation using Large Language Model
by: Mo, Zhengda, et al.
Published: (2026)

Conservative Decisions with Risk Scores
by: Wei, Yishu, et al.
Published: (2025)

Optimised Support Vector Regression for California Housing Price Prediction: The Critical Role of Feature Engineering and Hyperparameter Tuning
by: Adutwum, Emmanuel
Published: (2026)

Augmented Functional Random Forests: Classifier Construction and Unbiased Functional Principal Components Importance through Ad-Hoc Conditional Permutations
by: Maturo, Fabrizio, et al.
Published: (2024)

When Are Two RLHF Objectives the Same?
by: Gaikwad, Madhava
Published: (2025)

Intelligence Without Integrity: Why Capable LLMs May Undermine Reliability
by: Allen, Ryan, et al.
Published: (2026)

Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning
by: Basu, Abhinaba
Published: (2026)

Text Clustering with Large Language Model Embeddings
by: Petukhova, Alina, et al.
Published: (2024)

J6: Jacobian-Driven Role Attribution for Multi-Objective Prompt Optimization in LLMs
by: Wu, Yao
Published: (2025)

Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations
by: Mahale, Ajay Pravin
Published: (2026)

The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction
by: Wan, Shu, et al.
Published: (2026)

Federated Learning and Class Imbalances
by: Zhu, Siqi, et al.
Published: (2026)

SplitWise Regression: Stepwise Modeling with Adaptive Dummy Encoding
by: Kurbucz, Marcell T., et al.
Published: (2025)

Asymptotic Consistency and Generalization in Hybrid Models of Regularized Selection and Nonlinear Learning
by: Galvão, Luciano Ribeiro, et al.
Published: (2025)

Cross-Domain Uncertainty Quantification for Selective Prediction: A Comprehensive Bound Ablation with Transfer-Informed Betting
by: Basu, Abhinaba
Published: (2026)

The Trilemma of Truth in Large Language Models
by: Savcisens, Germans, et al.
Published: (2025)