conftrace_
← Core Methods
Machine Learning › Core Methods ›

Interpretability

499 papers

Papers per year

3
65
64
'15
'20
'25

Papers

On Relation-Specific Neurons in Large Language Models EMNLP 2025
ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering EMNLP 2025
Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework EMNLP 2025
Unsupervised Hallucination Detection by Inspecting Reasoning Processes EMNLP 2025
Interpretable Text Embeddings and Text Similarity Explanation: A Survey EMNLP 2025
Internal Chain-of-Thought: Empirical Evidence for Layer‐wise Subtask Scheduling in LLMs EMNLP 2025
Social Good or Scientific Curiosity? Uncovering the Research Framing Behind NLP Artefacts EMNLP 2025
Sparse Activation Editing for Reliable Instruction Following in Narratives EMNLP 2025
Explaining Differences Between Model Pairs in Natural Language through Sample Learning EMNLP 2025
AutoCT: Automating Interpretable Clinical Trial Prediction with LLM Agents EMNLP 2025
Discursive Circuits: How Do Language Models Understand Discourse Relations? EMNLP 2025
Language Models Identify Ambiguities and Exploit Loopholes EMNLP 2025
LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference EMNLP 2025
NormXLogit: The Head-on-Top Never Lies EMNLP 2025
Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding ICCV 2025
Interpretable DNFs IJCAI 2025
Interpretable Mesomorphic Networks for Tabular Data NIPS 2024
LLM-Check: Investigating Detection of Hallucinations in Large Language Models NIPS 2024
CoSy: Evaluating Textual Explanations of Neurons NIPS 2024
Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction NIPS 2024
Disentangling Interpretable Factors with Supervised Independent Subspace Principal Component Analysis NIPS 2024
LACIE: Listener-Aware Finetuning for Calibration in Large Language Models NIPS 2024
Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales NIPS 2024
Data-faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables NIPS 2024
Learning to Understand: Identifying Interactions via the Möbius Transform NIPS 2024