6 papers
Routing by Analogy: kNN-Augmented Expert Assignment for Mixture-of-Experts
Boxuan Lyu, Soichiro Murakami, Hidetaka Kamigaito +1
Mixture-of-Experts (MoE) architectures scale large language models efficiently by employing a parametric ``router'' to dispatch tokens to a sparse subset of experts. Typically, thi…
GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms
Masayuki Kawarada, Kodai Watanabe, Soichiro Murakami
We introduce GAIN (Goal-Aligned Decision-Making under Imperfect Norms), a benchmark designed to evaluate how large language models (LLMs) balance adherence to norms against busines…
Who Laughs with Whom? Disentangling Influential Factors in Humor Preferences across User Clusters and LLMs
Soichiro Murakami, Hidetaka Kamigaito, Hiroya Takamura +1
Humor preferences vary widely across individuals and cultures, complicating the evaluation of humor using large language models (LLMs). In this study, we model heterogeneity in hum…
Oogiri-Master: Benchmarking Humor Understanding via Oogiri
Soichiro Murakami, Hidetaka Kamigaito, Hiroya Takamura +1
Humor is a salient testbed for human-like creative thinking in large language models (LLMs). We study humor using the Japanese creative response game Oogiri, in which participants…
AdParaphrase v2.0: Generating Attractive Ad Texts Using a Preference-Annotated Paraphrase Dataset
Soichiro Murakami, Peinan Zhang, Hidetaka Kamigaito +2
Identifying factors that make ad text attractive is essential for advertising success. This study proposes AdParaphrase v2.0, a dataset for ad text paraphrasing, containing human p…
FaithCAMERA: Construction of a Faithful Dataset for Ad Text Generation
Akihiko Kato, Masato Mita, Soichiro Murakami +3
In ad text generation (ATG), desirable ad text is both faithful and informative. That is, it should be faithful to the input document, while at the same time containing important i…