Παρακολούθηση
Wenxuan Ding
Wenxuan Ding
The University of Texas at Austin
Η διεύθυνση ηλεκτρονικού ταχυδρομείου έχει επαληθευτεί στον τομέα utexas.edu - Αρχική σελίδα
Τίτλος
Παρατίθεται από
Παρατίθεται από
Έτος
Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration
S Feng, W Shi, Y Wang, W Ding, V Balachandran, Y Tsvetkov
arXiv preprint arXiv:2402.00367, 2024
572024
CAR: conceptualization-augmented reasoner for zero-shot commonsense question answering
W Wang, T Fang, W Ding, B Xu, X Liu, Y Song, A Bosselut
arXiv preprint arXiv:2305.14869, 2023
222023
CANDLE: iterative conceptualization and instantiation distillation from large language models for commonsense reasoning
W Wang, T Fang, C Li, H Shi, W Ding, B Xu, Z Wang, J Bai, X Liu, J Cheng, ...
arXiv preprint arXiv:2401.07286, 2024
182024
Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models
W Ding, S Feng, Y Liu, Z Tan, V Balachandran, T He, Y Tsvetkov
arXiv preprint arXiv:2310.01290, 2023
11*2023
MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding
B Xu, W Wang, H Shi, W Ding, H Jing, T Fang, J Bai, L Chen, Y Song
arXiv preprint arXiv:2406.10701, 2024
72024
On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions
W Wang, T Fang, H Shi, B Xu, W Ding, L Zhang, W Fan, J Bai, H Li, X Liu, ...
arXiv preprint arXiv:2406.10885, 2024
52024
IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce
W Ding, W Wang, SHD Kwok, M Liu, T Fang, J Bai, J He, Y Song
arXiv preprint arXiv:2406.10173, 2024
52024
QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering
H Shi, W Wang, T Fang, B Xu, W Ding, X Liu, Y Song
Findings of EMNLP 2023, 2023
42023
Teaching LLMs to Abstain across Languages via Multilingual Feedback
S Feng, W Shi, Y Wang, W Ding, O Ahia, SS Li, V Balachandran, ...
arXiv preprint arXiv:2406.15948, 2024
32024
Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
J Yao, W Ding, S Feng, LL Wang, Y Tsvetkov
arXiv preprint arXiv:2410.11055, 2024
12024
Δεν είναι δυνατή η εκτέλεση της ενέργειας από το σύστημα αυτή τη στιγμή. Προσπαθήστε ξανά αργότερα.
Άρθρα 1–10