conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7,318 papers

Papers per year

Papers

What Makes and Breaks Safety Fine-tuning? A Mechanistic Study NIPS 2024
Hypothesis Testing the Circuit Hypothesis in LLMs NIPS 2024
Grokking of Implicit Reasoning in Transformers: A Mechanistic Journey to the Edge of Generalization NIPS 2024
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark NIPS 2024
ContextCite: Attributing Model Generation to Context NIPS 2024
Evaluating language models as risk scores NIPS 2024
Benchmarking the Attribution Quality of Vision Models NIPS 2024
Do LLMs Build World Representations? Probing Through the Lens of State Abstraction NIPS 2024
Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction NIPS 2024
PaCE: Parsimonious Concept Engineering for Large Language Models NIPS 2024
Explanations that reveal all through the definition of encoding NIPS 2024
A theoretical design of concept sets: improving the predictability of concept bottleneck models NIPS 2024
Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems NIPS 2024
An Information Theoretic Perspective on Conformal Prediction NIPS 2024
UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation NIPS 2024
Saliency-driven Experience Replay for Continual Learning NIPS 2024
BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens NIPS 2024
Coarse-to-Fine Concept Bottleneck Models NIPS 2024
A Polar coordinate system represents syntax in large language models NIPS 2024
Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning NIPS 2024
Iteration Head: A Mechanistic Study of Chain-of-Thought NIPS 2024
Optimal ablation for interpretability NIPS 2024
Hierarchical Selective Classification NIPS 2024
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs NIPS 2024
Context-Aware Testing: A New Paradigm for Model Testing with Large Language Models NIPS 2024