arXiv subjects

Hideo Kobayashi

Publications and source records attributed to Hideo Kobayashi.

4 recordsLinked to original sources

arXiv2026

What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects

Table modeling has progressed for decades. In this work, we revisit this trajectory and highlight emerging challenges in the LLM era, particularly the paradox of choice: the difficulty of attributing performance gains amid diverse base models and training sets in the context of table instruction tuning. We replicate four table LLMs by instruction-tuning three foundation models on four existing datasets, yielding 12 models. We then evaluate these models across 16 table benchmarks. Our study is the first to quantitatively disentangle the effects of training data and base model selection, revealing that base model choice plays a more dominant role than the training data itself. Generalization and reasoning remain challenging, inviting future effort on table modeling. Based on our findings, we share our thoughts on the future directions for table modeling.

cs.CL↗

arXiv2025

DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation

Large language model (LLM) agents have shown promising performance in generating code for solving complex data science problems. Recent studies primarily focus on enhancing in-context learning through improved search, sampling, and planning techniques, while overlooking the importance of the order in which problems are tackled during inference. In this work, we develop a novel inference-time optimization framework, referred to as DSMentor, which leverages curriculum learning -- a strategy that introduces simpler task first and progressively moves to more complex ones as the learner improves -- to enhance LLM agent performance in challenging data science tasks. Our mentor-guided framework organizes data science tasks in order of increasing difficulty and incorporates a growing long-term memory to retain prior experiences, guiding the agent's learning progression and enabling more effective utilization of accumulated knowledge. We evaluate DSMentor through extensive experiments on DSEval and QRData benchmarks. Experiments show that DSMentor using Claude-3.5-Sonnet improves the pass rate by up to 5.2% on DSEval and QRData compared to baseline agents. Furthermore, DSMentor demonstrates stronger causal reasoning ability, improving the pass rate by 8.8% on the causality problems compared to GPT-4 using Program-of-Thoughts prompts. Our work underscores the importance of developing effective strategies for accumulating and utilizing knowledge during inference, mirroring the human learning process and opening new avenues for improving LLM performance through curriculum-based inference optimization.

cs.AI↗

arXiv2024

You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL

While significant progress has been made on the text-to-SQL task, recent solutions repeatedly encode the same database schema for every question, resulting in unnecessary high inference cost and often overlooking crucial database knowledge. To address these issues, we propose You Only Read Once (YORO), a novel paradigm that directly internalizes database knowledge into the parametric knowledge of a text-to-SQL model during training and eliminates the need for schema encoding during inference. YORO significantly reduces the input token length by 66%-98%. Despite its shorter inputs, our empirical results demonstrate YORO's competitive performances with traditional systems on three benchmarks as well as its significant outperformance on large databases. Furthermore, YORO excels in handling questions with challenging value retrievals such as abbreviation.

cs.CL↗

arXiv2003

Properties and Curie Temperature (130 K) of Heavily Mn-doped Quaternary Alloy Ferromagnetic Semiconductor (InGaMn)As Grown on InP

We have studied magnetic properties of heavily Mn-doped [(In0.44Ga0.56)0.79Mn0.21]As thin films grown by low-temperature molecular-beam epitaxy (LT-MBE) on InP substrates. The (InGaMn)As with high Mn content (21%) was obtained by decreasing the growth temperature to 190 degC. When the thickness of the [(In0.44Ga0.56)0.79Mn0.21]As layer is equal or thinner than 10 nm, the reflection high-energy electron diffraction (RHEED) pattern and transmission electron microscopy (TEM) show no MnAs clustering, indicating that a homogeneous single crystal with good quality was grown. In the magnetic circular dicroism (MCD) measurement, large MCD intensity and high Curie temperature of 130 K were observed.

cond-mat.mtrl-sci↗