Interpretability

Tracking Perspectives on Event Participants: a Structural Analysis of the Framing of Real-World Events in Co-Referential Corpora COLING 2024 Tracking the Newsworthiness of Public Documents ACL 2024 Trained Random Forests Completely Reveal your Dataset ICML 2024 Training Data Attribution via Approximate Unrolling NeurIPS 2024 Training for Stable Explanation for Free NeurIPS 2024 Transcoders find interpretable LLM feature circuits NeurIPS 2024 Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking ACL 2024 Transformer Attention vs Human Attention in Anaphora Resolution ACL 2024 Transformer-based Joint Modelling for Automatic Essay Scoring and Off-Topic Detection COLING 2024 Transformer Doctor: Diagnosing and Treating Vision Transformers NeurIPS 2024 Transformer-specific Interpretability EACL 2024 Transformers Represent Belief State Geometry in their Residual Stream NeurIPS 2024 Transitional Uncertainty with Layered Intermediate Predictions ICML 2024 Translation Canvas: An Explainable Interface to Pinpoint and Analyze Translation Systems EMNLP 2024 Transparent and Scrutable Recommendations Using Natural Language User Profiles ACL 2024 Triple-R: Automatic Reasoning for Fact Verification Using Language Models COLING 2024 Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning ICML 2024 Trusting Your Evidence: Hallucinate Less with Context-aware Decoding NAACL 2024 Trust Regions for Explanations via Black-Box Probabilistic Certification ICML 2024 Trustworthiness and Self-awareness in Large Language Models: An Exploration through the Think-Solve-Verify Framework COLING 2024 Trustworthy Actionable Perturbations ICML 2024 Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts ACL 2024 Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning AAAI 2024 Truthfulness of Calibration Measures NeurIPS 2024 Truth is Universal: Robust Detection of Lies in LLMs NeurIPS 2024