Resultados de búsqueda - Hong, Pingjun

Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations por Hong, Pingjun, Roth, Benjamin

Enlace del recurso

Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales por Hong, Pingjun, Roth, Benjamin

Enlace del recurso

Evaluating Large Language Models for Cross-Lingual Retrieval por Zuo, Longfei, Hong, Pingjun, Kraus, Oliver, Plank, Barbara, Litschko, Robert

Enlace del recurso

LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference por Hong, Pingjun, Chen, Beiduo, Peng, Siyao, de Marneffe, Marie-Catherine, Plank, Barbara

Enlace del recurso

Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization por Chen, Beiduo, Hong, Pingjun, Zhang, Ziyun, Roth, Benjamin, Korhonen, Anna, Plank, Barbara

Enlace del recurso

Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations por Hong, Pingjun, Chen, Beiduo, Peng, Siyao, de Marneffe, Marie-Catherine, Roth, Benjamin, Plank, Barbara

Enlace del recurso

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy por Shen, Xu, Tan, Zhen, Wang, Song, Hong, Pingjun, Miao, Rui, Wang, Xin, Chen, Tianlong

Enlace del recurso