LTLBench: Towards Benchmarks for Evaluating Temporal Logic Reasoning in Large Language Models. Tang, W. & Belle, V. CoRR, 2024. Paper doi bibtex @article{DBLP:journals/corr/abs-2407-05434,
author = {Weizhi Tang and
Vaishak Belle},
title = {LTLBench: Towards Benchmarks for Evaluating Temporal Logic Reasoning
in Large Language Models},
journal = {CoRR},
volume = {abs/2407.05434},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2407.05434},
doi = {10.48550/ARXIV.2407.05434},
eprinttype = {arXiv},
eprint = {2407.05434},
timestamp = {Mon, 12 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2407-05434.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
Downloads: 0
{"_id":"iP4nTPFryv24fMML4","bibbaseid":"tang-belle-ltlbenchtowardsbenchmarksforevaluatingtemporallogicreasoninginlargelanguagemodels-2024","author_short":["Tang, W.","Belle, V."],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Weizhi"],"propositions":[],"lastnames":["Tang"],"suffixes":[]},{"firstnames":["Vaishak"],"propositions":[],"lastnames":["Belle"],"suffixes":[]}],"title":"LTLBench: Towards Benchmarks for Evaluating Temporal Logic Reasoning in Large Language Models","journal":"CoRR","volume":"abs/2407.05434","year":"2024","url":"https://doi.org/10.48550/arXiv.2407.05434","doi":"10.48550/ARXIV.2407.05434","eprinttype":"arXiv","eprint":"2407.05434","timestamp":"Mon, 12 Aug 2024 01:00:00 +0200","biburl":"https://dblp.org/rec/journals/corr/abs-2407-05434.bib","bibsource":"dblp computer science bibliography, https://dblp.org","bibtex":"@article{DBLP:journals/corr/abs-2407-05434,\n author = {Weizhi Tang and\n Vaishak Belle},\n title = {LTLBench: Towards Benchmarks for Evaluating Temporal Logic Reasoning\n in Large Language Models},\n journal = {CoRR},\n volume = {abs/2407.05434},\n year = {2024},\n url = {https://doi.org/10.48550/arXiv.2407.05434},\n doi = {10.48550/ARXIV.2407.05434},\n eprinttype = {arXiv},\n eprint = {2407.05434},\n timestamp = {Mon, 12 Aug 2024 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2407-05434.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n","author_short":["Tang, W.","Belle, V."],"key":"DBLP:journals/corr/abs-2407-05434","id":"DBLP:journals/corr/abs-2407-05434","bibbaseid":"tang-belle-ltlbenchtowardsbenchmarksforevaluatingtemporallogicreasoninginlargelanguagemodels-2024","role":"author","urls":{"Paper":"https://doi.org/10.48550/arXiv.2407.05434"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://dblp.org/pid/52/570.bib","dataSources":["ayruv4JDJNMLz7ieC","qb6u34NNzEHCho66A","o8SJynH3ZqhBLq3sp","7PCTuJcihysb7xARD"],"keywords":[],"search_terms":["ltlbench","towards","benchmarks","evaluating","temporal","logic","reasoning","large","language","models","tang","belle"],"title":"LTLBench: Towards Benchmarks for Evaluating Temporal Logic Reasoning in Large Language Models","year":2024}