conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7,318 papers

Papers per year

Papers

Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems? IJCNLP 2025
Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge IJCNLP 2025
How Reliable are Causal Probing Interventions? IJCNLP 2025
Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length? IJCNLP 2025
Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models IJCNLP 2025
On the Convergence of Moral Self-Correction in Large Language Models IJCNLP 2025
Fine-grained Confidence Estimation for Spurious Correctness Detection in Large Language Models IJCNLP 2025
SciHallu: A Multi-Granularity Hallucination Detection Dataset for Scientific Writing IJCNLP 2025
ProofTeller: Exposing recency bias in LLM reasoning and its side effects on communication IJCNLP 2025
Exploring Working Memory Capacity in LLMs: From Stressors to Human-Inspired Strategies IJCNLP 2025
The Visual Counter Turing Test (VCT²): A Benchmark for Evaluating AI-Generated Image Detection and the Visual AI Index (V_AI) IJCNLP 2025
The Confidence Paradox: Can LLM Know When It’s Wrong? IJCNLP 2025
Are Humans as Brittle as Large Language Models? IJCNLP 2025
PerCoR: Evaluating Commonsense Reasoning in Persian via Multiple-Choice Sentence Completion IJCNLP 2025
Interpreting the Effects of Quantization on LLMs IJCNLP 2025
Large Language Models Encode Semantics and Alignment in Linearly Separable Representations IJCNLP 2025
Hallucinations in Code Change to Natural Language Generation: Prevalence and Evaluation of Detection Metrics IJCNLP 2025
A Diagnostic Framework for Auditing Reference-Free Vision-Language Metrics IJCNLP 2025
Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning IJCNLP 2025
Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation IJCNLP 2025
Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies IJCNLP 2025
ContrastScore: Towards Higher Quality, Less Biased, More Efficient Evaluation Metrics with Contrastive Evaluation IJCNLP 2025
ReasoningWeekly: A General Knowledge and Verbal Reasoning Challenge for Large Language Models IJCNLP 2025
Cascaded Information Disclosure for Generalized Evaluation of Problem Solving Capabilities IJCNLP 2025
Is OpenVLA Truly Robust? A Systematic Evaluation of Positional Robustness IJCNLP 2025