Mengyu Ye (@muyo8692) 's Twitter Profile
Mengyu Ye

@muyo8692

PhD student at Tohoku University, Japan (Tohoku NLP lab. @tohoku_nlp)
#NLProc

ID: 1717729194111827968

linkhttps://muyo8692.github.io/ calendar_today27-10-2023 02:25:46

2 Tweet

54 Followers

67 Following

Gate.io (@gate_io) 's Twitter Profile Photo
Gate.io
@gate_io

5 hours ago

🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358
Mengyu Ye (@muyo8692) 's Twitter Profile Photo
Mengyu Ye
@muyo8692

2 years ago

Is it plausible that LLMs can handle lexical negation? —No Is it im-plausible that LLMs can handle lexical negation? —Yes LLMs systematically struggle with such negation during CoT-style reasoning in our controlled experiments🤯 Check our #EMNLP2023 paper: arxiv.org/abs/2310.14868

Is it plausible that LLMs can handle lexical negation? —No Is it im-plausible that LLMs can handle lexical negation? —Yes LLMs systematically struggle with such negation during CoT-style reasoning in our controlled experiments🤯 Check our #EMNLP2023 paper: arxiv.org/abs/2310.14868
Mengyu Ye (@muyo8692) 's Twitter Profile Photo
Mengyu Ye
@muyo8692

2 years ago

初めての研究が #EMNLP2023 に採択されました！！#NLP2023 で発表し、ACL-SRWでSRW Best Paper Awardをいただいた研究の拡張版です。 大規模言語モデルは「plausible -> implausible」のような語彙的否定に頑丈性がないことを示しました。 Tohoku NLP Group (migrated to @tohoku_nlp) で取り組んだ成果です。