conftrace_

model introspection

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

german language processing (1) knowledge calibration (1) hypothetical reasoning (1) introspection technique (1) input visualization (1) subject-object resolution (1) causal steering (1) privileged access (1) hubert model (1) transformer attention (1)

Papers

Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering ACL 2026 Looking Inward: Language Models Can Learn About Themselves by Introspection ICLR 2025 Do Large Language Models Know How Much They Know? EMNLP 2024 Topological Data Analysis for Speech Processing Interspeech 2023 When Beards Start Shaving Men: A Subject-object Resolution Test Suite for Morpho-syntactic and Semantic Model Introspection COLING 2020 Introspection for convolutional automatic speech recognition EMNLP 2018