conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7,318 papers

Papers per year

Papers

ALiiCE: Evaluating Positional Fine-grained Citation Generation NAACL 2025
On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs NAACL 2025
Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models NAACL 2025
Reversed Attention: On The Gradient Descent Of Attention Layers In GPT NAACL 2025
RAP: A Metric for Balancing Repetition and Performance in Open-Source Large Language Models NAACL 2025
What Did I Do Wrong? Quantifying LLMs’ Sensitivity and Consistency to Prompt Engineering NAACL 2025
Option Symbol Matters: Investigating and Mitigating Multiple-Choice Option Symbol Bias of Large Language Models NAACL 2025
Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models NAACL 2025
An Interpretable and Crosslingual Method for Evaluating Second-Language Dialogues NAACL 2025
Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization NAACL 2025
Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models NAACL 2025
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks NAACL 2025
SafeQuant: LLM Safety Analysis via Quantized Gradient Inspection NAACL 2025
NLI under the Microscope: What Atomic Hypothesis Decomposition Reveals NAACL 2025
Benchmarking Language Model Creativity: A Case Study on Code Generation NAACL 2025
Probe-Free Low-Rank Activation Intervention NAACL 2025
Racing Thoughts: Explaining Contextualization Errors in Large Language Models NAACL 2025
A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation NAACL 2025
Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models NAACL 2025
Extracting and Understanding the Superficial Knowledge in Alignment NAACL 2025
LLM The Genius Paradox: A Linguistic and Math Expert’s Struggle with Simple Word-based Counting Problems NAACL 2025
Who Relies More on World Knowledge and Bias for Syntactic Ambiguity Resolution: Humans or LLMs? NAACL 2025
Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions NAACL 2025
What We Talk About When We Talk About LMs: Implicit Paradigm Shifts and the Ship of Language Models NAACL 2025
MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation NAACL 2025