conftrace_

model internal

7 papers

Explore in graph

Co-occurring keywords

large language model (13587) subnetwork extraction (7) pretrained language model (1030) internal representation (49) gender bia (435) citation generation (40) attention pattern (45) probing classifier (40) encoder architecture (27) model understanding (7)

Papers

Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis EMNLP 2025

“I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents EMNLP 2025

Gender Encoding Patterns in Pretrained Language Model Representations NAACL 2025

Hypothesis Testing the Circuit Hypothesis in LLMs NIPS 2024

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation EMNLP 2024

Do Large Language Models Know How Much They Know? EMNLP 2024

Language Models Understand Us, Poorly EMNLP 2022