conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7,318 papers

Papers per year

Papers

Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms EMNLP 2025
NCL-UoR at SemEval-2025 Task 3: Detecting Multilingual Hallucination and Related Observable Overgeneration Text Spans with Modified RefChecker and Modified SelfCheckGPT SEMEVAL 2025
Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling NIPS 2024
Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders NIPS 2024
LLaNA: Large Language and NeRF Assistant NIPS 2024
Diffusion PID: Interpreting Diffusion via Partial Information Decomposition NIPS 2024
Training for Stable Explanation for Free NIPS 2024
Data Attribution for Text-to-Image Models by Unlearning Synthesized Images NIPS 2024
Verifiably Robust Conformal Prediction NIPS 2024
Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution NIPS 2024
IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons NIPS 2024
Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scary NIPS 2024
Multi-Label Open Set Recognition NIPS 2024
Exploiting Representation Curvature for Boundary Detection in Time Series NIPS 2024
Understanding Information Storage and Transfer in Multi-Modal Large Language Models NIPS 2024
Reproducibility of predictive networks for mouse visual cortex NIPS 2024
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology NIPS 2024
Image-aware Evaluation of Generated Medical Reports NIPS 2024
Exploring Context Window of Large Language Models via Decomposed Positional Vectors NIPS 2024
ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks NIPS 2024
I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token NIPS 2024
Typicalness-Aware Learning for Failure Detection NIPS 2024
How Diffusion Models Learn to Factorize and Compose NIPS 2024
Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control NIPS 2024
Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads NIPS 2024