Hayate Iso

41 papers A* 3B 4Journal 21Unranked 13
YearRankTypeTitle / Venue / Authors
2025 — conf
Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and Education.
NAACL (Industry Track)
Hayate Iso, Pouya Pezeshkpour, Nikita Bhutani, Estevam Hruschka
2025 J jnl
Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and Education.
CoRR
Hayate Iso, Pouya Pezeshkpour, Nikita Bhutani, Estevam Hruschka
2025 — conf
From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization.
NAACL (Findings)
Catarina G. Belém, Pouya Pezeshkpour, Hayate Iso, Seiji Maekawa, Nikita Bhutani, Estevam Hruschka
2025 A* conf
Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data.
ICLR
Seiji Maekawa, Hayate Iso, Nikita Bhutani
2025 J jnl
The Rarity Blind Spot: A Framework for Evaluating Statistical Reasoning in LLMs.
CoRR
Seiji Maekawa, Hayate Iso, Nikita Bhutani
2024 J jnl
A Blueprint Architecture of Compound AI Systems for Enterprise.
CoRR
Eser Kandogan, Sajjadur Rahman, Nikita Bhutani, Dan Zhang, Rafael Li Chen, Kushan Mitra, Sairam Gurajada, Pouya Pezeshkpour, Hayate Iso, Yanlin Feng, Hannah Kim, Chen Shen, Jin Wang, Estevam Hruschka
2024 A* conf
AmbigNLG: Addressing Task Ambiguity in Instruction for NLG.
EMNLP
Ayana Niwa, Hayate Iso
2024 J jnl
AmbigNLG: Addressing Task Ambiguity in Instruction for NLG.
CoRR
Ayana Niwa, Hayate Iso
2024 B conf
AutoTemplate: A Simple Recipe for Lexically Constrained Text Generation.
INLG
Hayate Iso
2024 J jnl
From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization.
CoRR
Catarina G. Belém, Pouya Pezeskhpour, Hayate Iso, Seiji Maekawa, Nikita Bhutani, Estevam Hruschka
2024 J jnl
Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data.
CoRR
Seiji Maekawa, Hayate Iso, Nikita Bhutani
2024 — conf
Less is More for Long Document Summary Evaluation by LLMs.
EACL (2)
Yunshu Wu, Hayate Iso, Pouya Pezeshkpour, Nikita Bhutani, Estevam Hruschka
2024 J jnl
Less is More for Long Document Summary Evaluation by LLMs.
J. Nat. Lang. Process.
Hayate Iso
2024 B conf
Noisy Pairing and Partial Supervision for Stylized Opinion Summarization.
INLG
Hayate Iso, Xiaolan Wang, Yoshi Suhara
2024 — conf
Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models.
NAACL-HLT
Seiji Maekawa, Hayate Iso, Sairam Gurajada, Nikita Bhutani
2024 J jnl
Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models.
CoRR
Seiji Maekawa, Hayate Iso, Sairam Gurajada, Nikita Bhutani
2024 — conf
XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates.
LREC/COLING
Haopeng Zhang, Hayate Iso, Sairam Gurajada, Nikita Bhutani
2023 J jnl
Distilling Large Language Models using Skill-Occupation Graph Context for HR-Related Tasks.
CoRR
Pouya Pezeshkpour, Hayate Iso, Thom Lake, Nikita Bhutani, Estevam Hruschka
2023 J jnl
Less is More for Long Document Summary Evaluation by LLMs.
CoRR
Yunshu Wu, Hayate Iso, Pouya Pezeshkpour, Nikita Bhutani, Estevam Hruschka
2023 J jnl
XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates.
CoRR
Haopeng Zhang, Hayate Iso, Sairam Gurajada, Nikita Bhutani
2023 — conf
Zero-shot Triplet Extraction by Template Infilling.
IJCNLP (1)
Bosung Kim, Hayate Iso, Nikita Bhutani, Estevam Hruschka, Ndapa Nakashole, Tom M. Mitchell
2022 J jnl
AutoTemplate: A Simple Recipe for Lexically Constrained Text Generation.
CoRR
Hayate Iso
2022 — conf
Comparative Opinion Summarization via Collaborative Decoding.
ACL (Findings)
Hayate Iso, Xiaolan Wang, Stefanos Angelidis, Yoshihiko Suhara
2022 J jnl
Noisy Pairing and Partial Supervision for Opinion Summarization.
CoRR
Hayate Iso, Xiaolan Wang, Yoshi Suhara
2022 J jnl
Zero-shot Triplet Extraction by Template Infilling.
CoRR
Bosung Kim, Hayate Iso, Nikita Bhutani, Estevam Hruschka, Ndapa Nakashole
2021 J jnl
Biomedical Entity Linking with Contrastive Context Matching.
CoRR
Shogo Ujiie, Hayate Iso, Eiji Aramaki
2021 J jnl
Comparative Opinion Summarization via Collaborative Decoding.
CoRR
Hayate Iso, Xiaolan Wang, Yoshihiko Suhara
2021 — conf
Convex Aggregation for Opinion Summarization.
EMNLP (Findings)
Hayate Iso, Xiaolan Wang, Yoshihiko Suhara, Stefanos Angelidis, Wang-Chiew Tan
2021 J jnl
Convex Aggregation for Opinion Summarization.
CoRR
Hayate Iso, Xiaolan Wang, Yoshihiko Suhara, Stefanos Angelidis, Wang-Chiew Tan
2021 — conf
End-to-end Biomedical Entity Linking with Span-based Dictionary Matching.
BioNLP@NAACL-HLT
Shogo Ujiie, Hayate Iso, Shuntaro Yada, Shoko Wakamiya, Eiji Aramaki
2021 J jnl
End-to-end Biomedical Entity Linking with Span-based Dictionary Matching.
CoRR
Shogo Ujiie, Hayate Iso, Shuntaro Yada, Shoko Wakamiya, Eiji Aramaki
2020 A* conf
Fact-based Text Editing.
ACL
Hayate Iso, Chao Qiao, Hang Li
2020 J jnl
Fact-based Text Editing.
CoRR
Hayate Iso, Chao Qiao, Hang Li
2019 — conf
Learning to Select, Track, and Generate for Data-to-Text.
ACL (1)
Hayate Iso, Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, Eiji Aramaki, Ichiro Kobayashi, Yusuke Miyao, Naoaki Okazaki, Hiroya Takamura
2019 J jnl
Learning to Select, Track, and Generate for Data-to-Text.
CoRR
Hayate Iso, Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, Eiji Aramaki, Ichiro Kobayashi, Yusuke Miyao, Naoaki Okazaki, Hiroya Takamura
2018 B conf
Wisdom in Adversity: A Twitter Study of the Japanese Tsunami.
ASONAM
Paolo Casani, Hayate Iso, Shoko Wakamiya, Eiji Aramaki
2017 — conf
Conditional Density Estimation of Tweet Location: A Feature-Dependent Approach.
MedInfo
Hayate Iso, Shoko Wakamiya, Eiji Aramaki
2017 J jnl
Density Estimation for Geolocation via Convolutional Mixture Density Network.
CoRR
Hayate Iso, Shoko Wakamiya, Eiji Aramaki
2017 — conf
Multivariate Linear Regression of Symptoms-related Tweets for Infectious Gastroenteritis Scale Estimation.
DDDSM@IJCNLP
Ryo Takeuchi, Hayate Iso, Kaoru Ito, Shoko Wakamiya, Eiji Aramaki
2017 — conf
NTCIR13 MedWeb Task: multi-label classification of tweets using an ensemble of neural networks.
NTCIR
Hayate Iso, Camille Ruiz, Taichi Murayama, Katsuya Taguchi, Ryo Takeuchi, Hideya Yamamoto, Shoko Wakamiya, Eiji Aramaki
2016 B conf
Forecasting Word Model: Twitter-based Influenza Surveillance and Prediction.
COLING
Hayate Iso, Shoko Wakamiya, Eiji Aramaki