arXiv subjects

Ting Cai

Publications and source records attributed to Ting Cai.

14 recordsLinked to original sources

arXiv2026

Polaris: Learning to Generate Table Descriptions from Retrieval Feedback

Many table-centric NLP tasks such as NL2SQL first retrieve relevant tables from large collections using keyword search. Recent work uses LLMs to generate natural-language table descriptions to improve retrieval, but they are typically optimized for fluency rather than retrieval effectiveness. We present Polaris, a system that trains an LLM to generate table descriptions directly from retrieval feedback. Our key insight is that existing table retrieval benchmarks already contain the supervision needed for this task: given query-table relevance judgments, we generate multiple candidate descriptions for each table, rank them by their BM25 retrieval effectiveness, and use the resulting preference pairs to fine-tune the LLM with Direct Preference Optimization (DPO). Polaris further expands abbreviated table and column names before generation to reduce vocabulary mismatch. Extensive experiments show that Polaris outperforms the state-of-the-art AutoDDG solution, often by a significant margin. More broadly, our results demonstrate that retrieval benchmarks can be repurposed as supervision for training LLMs to generate retrieval-oriented metadata.

cs.CL↗

arXiv2026

TACO: Task-Aware Column Description Generation Using LLMs

Generating accurate and informative column descriptions (e.g. "membership status of customers" for the column name "cust_mem") is essential for a wide range of downstream NLP tasks on tabular data, including NL2SQL, table question answering, and entity linking. This problem arises in enterprises, domain sciences, government data portals, and so on. Despite its importance, most real-world datasets suffer from missing or cryptic documentation, often due to abbreviated column names or domain-specific jargon. Existing approaches largely rely on single-prompt large language models (LLMs), which struggle with three key issues: (i) inconsistent or incorrect handling of abbreviations, (ii) hallucinated or incomplete descriptions, and (iii) redundancy or vagueness that hinders downstream performance. We present TACO, a task-aware framework for automatic column description generation using LLMs. TACO introduces a three-step pipeline: (1) abbreviation expansion, which standardizes column names; (2) description generation, which produces initial semantic descriptions enriched with synonyms and search-oriented keywords; and (3) description revision, which refines these outputs using simulated downstream tasks. In addition, we investigate human-in-the-loop extensions and release new evaluation datasets for entity linking and schema enrichment. Extensive experiments across public and proprietary datasets show that TACO consistently outperforms existing methods, improving downstream task performance by up to 32%.

cs.CL↗

arXiv2026

ISEE: Interactive Semantic Enrichment for Database Fields

LLM-based agents are increasingly being deployed for data-related tasks, including data sense-making, exploration, and retrieval. However, their performance heavily depends on the clarity and completeness of data semantics. In practice, many field descriptions remain ambiguous or incomplete, as much of the essential context (e.g., the meaning of a customized field) originates from users' domain knowledge and is rarely documented publicly. This gap restricts the agents' task performance in downstream tasks, such as entity-linking. To bridge this gap, we introduce a novel and comprehensive Interactive SEmantic Enrichment system (ISEE). Given a data field description, ISEE measures its quality through a scoring system, gathers domain knowledge, and collaboratively enriches the semantics with users. Through a user study, automated user simulation, quantitative evaluation, and case study, we demonstrate that ISEE significantly reduces cognitive load, improves description quality, and enhances downstream task performance.

cs.AI↗

arXiv2026

Rethinking Basis Path Testing: Mixed Integer Programming Approach for Test Path Set Generation

Basis path testing is a cornerstone of structural testing, yet traditional automated methods, relying on greedy graph-traversal algorithms (e.g., DFS/BFS), often generate sub-optimal paths. This structural inferiority is not a trivial issue; it directly impedes downstream testing activities by complicating automated test data generation and increasing the cognitive load for human engineers. This paper reframes basis path generation from a procedural search task into a declarative optimization problem. We introduce a Mixed Integer Programming (MIP) framework designed to produce a complete basis path set that is globally optimal in its structural simplicity. Our framework includes two complementary strategies: a Holistic MIP model that guarantees a theoretically optimal path set, and a scalable Incremental MIP strategy for large, complex topologies. The incremental approach features a multi-objective function that prioritizes path simplicity and incorporates a novelty penalty to maximize the successful generation of linearly independent paths. Empirical evaluations on both real-code and large-scale synthetic Control Flow Graphs demonstrate that our Incremental MIP strategy achieves a 100\% success rate in generating complete basis sets, while remaining computationally efficient. Our work provides a foundational method for generating a high-quality structural "scaffold" that can enhance the efficiency and effectiveness of subsequent test generation efforts.

cs.SE↗

arXiv2025

Constrained Best Arm Identification with Tests for Feasibility

Best arm identification (BAI) aims to identify the highest-performance arm among a set of $K$ arms by collecting stochastic samples from each arm. In real-world problems, the best arm needs to satisfy additional feasibility constraints. While there is limited prior work on BAI with feasibility constraints, they typically assume the performance and constraints are observed simultaneously on each pull of an arm. However, this assumption does not reflect most practical use cases, e.g., in drug discovery, we wish to find the most potent drug whose toxicity and solubility are below certain safety thresholds. These safety experiments can be conducted separately from the potency measurement. Thus, this requires designing BAI algorithms that not only decide which arm to pull but also decide whether to test for the arm's performance or feasibility. In this work, we study feasible BAI which allows a decision-maker to choose a tuple $(i,\ell)$, where $i\in [K]$ denotes an arm and $\ell$ denotes whether she wishes to test for its performance ($\ell=0$) or any of its $N$ feasibility constraints ($\ell\in[N]$). We focus on the fixed confidence setting, which is to identify the feasible arm with the highest performance, with a probability of at least $1-\delta$. We propose an efficient algorithm and upper-bound its sample complexity, showing our algorithm can naturally adapt to the problem's difficulty and eliminate arms by worse performance or infeasibility, whichever is easier. We complement this upper bound with a lower bound showing that our algorithm is \textit{asymptotically ($\delta\rightarrow 0$) optimal}. Finally, we empirically show that our algorithm outperforms other state-of-the-art BAI algorithms in both synthetic and real-world datasets.

cs.LG↗

arXiv2025

Language Modeling With Factorization Memory

We propose Factorization Memory, an efficient recurrent neural network (RNN) architecture that achieves performance comparable to Transformer models on short-context language modeling tasks while also demonstrating superior generalization in long-context scenarios. Our model builds upon Mamba-2, enabling Factorization Memory to exploit parallel computations during training while preserving constant computational and memory complexity during inference. To further optimize model efficiency and representational capacity, we develop a sparse formulation of Factorization Memory that updates only a subset of recurrent states at each step while preserving the strong performance of its dense counterpart. To our knowledge, this represents the first RNN architecture that successfully combines sparse memory activation with competitive performance across both short and long-context settings. This work provides a systematic empirical analysis of Factorization Memory in comparison to Transformer and Mamba-2 architectures.

cs.CL↗

arXiv2025

Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Models

Expanding the abbreviated column names of tables, such as "esal" to "employee salary", is critical for many downstream NLP tasks for tabular data, such as NL2SQL, table QA, and keyword search. This problem arises in enterprises, domain sciences, government agencies, and more. In this paper, we make three contributions that significantly advance the state of the art. First, we show that the synthetic public data used by prior work has major limitations, and we introduce four new datasets in enterprise/science domains, with real-world abbreviations. Second, we show that accuracy measures used by prior work seriously undercount correct expansions, and we propose new synonym-aware measures that capture accuracy much more accurately. Finally, we develop Columbo, a powerful LLM-based solution that exploits context, rules, chain-of-thought reasoning, and token-level analysis. Extensive experiments show that Columbo significantly outperforms NameGuess, the current most advanced solution, by 4-29%, over five datasets. Columbo has been used in production on EDI, a major data lake for environmental sciences.

cs.CL↗

arXiv2025

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing

Efficient state restoration in multi-turn conversations with large language models (LLMs) remains a critical challenge, primarily due to the overhead of recomputing or loading full key-value (KV) caches for all historical tokens. To address this, existing approaches compress KV caches across adjacent layers with highly similar attention patterns. However, these methods often apply a fixed compression scheme across all conversations, selecting the same layer pairs for compression without considering conversation-specific attention dynamics. This static strategy overlooks variability in attention pattern similarity across different conversations, which can lead to noticeable accuracy degradation. We present Krul, a multi-turn LLM inference system that enables accurate and efficient KV cache restoration. Krul dynamically selects compression strategies based on attention similarity across layer pairs and uses a recomputation-loading pipeline to restore the KV cache. It introduces three key innovations: 1) a preemptive compression strategy selector to preserve critical context for future conversation turns and selects a customized strategy for the conversation; 2) a token-wise heterogeneous attention similarity estimator to mitigate the attention similarity computation and storage overhead during model generation; 3) a bubble-free restoration scheduler to reduce potential bubbles brought by the imbalance of recomputing and loading stream due to compressed KV caches. Empirical evaluations on real-world tasks demonstrate that Krul achieves a 1.5x-2.68x reduction in time-to-first-token (TTFT) and a 1.33x-2.35x reduction in KV cache storage compared to state-of-the-art methods without compromising generation quality.

cs.CL↗

arXiv2024

RakutenAI-7B: Extending Large Language Models for Japanese

We introduce RakutenAI-7B, a suite of Japanese-oriented large language models that achieve the best performance on the Japanese LM Harness benchmarks among the open 7B models. Along with the foundation model, we release instruction- and chat-tuned models, RakutenAI-7B-instruct and RakutenAI-7B-chat respectively, under the Apache 2.0 license.

cs.CL↗

arXiv2023

Active Cost-aware Labeling of Streaming Data

We study actively labeling streaming data, where an active learner is faced with a stream of data points and must carefully choose which of these points to label via an expensive experiment. Such problems frequently arise in applications such as healthcare and astronomy. We first study a setting when the data's inputs belong to one of $K$ discrete distributions and formalize this problem via a loss that captures the labeling cost and the prediction error. When the labeling cost is $B$, our algorithm, which chooses to label a point if the uncertainty is larger than a time and cost dependent threshold, achieves a worst-case upper bound of $\widetilde{O}(B^{\frac{1}{3}} K^{\frac{1}{3}} T^{\frac{2}{3}})$ on the loss after $T$ rounds. We also provide a more nuanced upper bound which demonstrates that the algorithm can adapt to the arrival pattern, and achieves better performance when the arrival pattern is more favorable. We complement both upper bounds with matching lower bounds. We next study this problem when the inputs belong to a continuous domain and the output of the experiment is a smooth function with bounded RKHS norm. After $T$ rounds in $d$ dimensions, we show that the loss is bounded by $\widetilde{O}(B^{\frac{1}{d+3}} T^{\frac{d+2}{d+3}})$ in an RKHS with a squared exponential kernel and by $\widetilde{O}(B^{\frac{1}{2d+3}} T^{\frac{2d+2}{2d+3}})$ in an RKHS with a Mat\'ern kernel. Our empirical evaluation demonstrates that our method outperforms other baselines in several synthetic experiments and two real experiments in medicine and astronomy.

cs.LG↗

arXiv2021

MVCNet: Multiview Contrastive Network for Unsupervised Representation Learning for 3D CT Lesions

\emph{Objective and Impact Statement}. With the renaissance of deep learning, automatic diagnostic systems for computed tomography (CT) have achieved many successful applications. However, they are mostly attributed to careful expert annotations, which are often scarce in practice. This drives our interest to the unsupervised representation learning. \emph{Introduction}. Recent studies have shown that self-supervised learning is an effective approach for learning representations, but most of them rely on the empirical design of transformations and pretext tasks. \emph{Methods}. To avoid the subjectivity associated with these methods, we propose the MVCNet, a novel unsupervised three dimensional (3D) representation learning method working in a transformation-free manner. We view each 3D lesion from different orientations to collect multiple two dimensional (2D) views. Then, an embedding function is learned by minimizing a contrastive loss so that the 2D views of the same 3D lesion are aggregated, and the 2D views of different lesions are separated. We evaluate the representations by training a simple classification head upon the embedding layer. \emph{Results}. Experimental results show that MVCNet achieves state-of-the-art accuracies on the LIDC-IDRI (89.55\%), LNDb (77.69\%) and TianChi (79.96\%) datasets for \emph{unsupervised representation learning}. When fine-tuned on 10\% of the labeled data, the accuracies are comparable to the supervised learning model (89.46\% vs. 85.03\%, 73.85\% vs. 73.44\%, 83.56\% vs. 83.34\% on the three datasets, respectively). \emph{Conclusion}. Results indicate the superiority of MVCNet in \emph{learning representations with limited annotations}.

cs.CV↗

arXiv2021

Adversarially-Trained Nonnegative Matrix Factorization

We consider an adversarially-trained version of the nonnegative matrix factorization, a popular latent dimensionality reduction technique. In our formulation, an attacker adds an arbitrary matrix of bounded norm to the given data matrix. We design efficient algorithms inspired by adversarial training to optimize for dictionary and coefficient matrices with enhanced generalization abilities. Extensive simulations on synthetic and benchmark datasets demonstrate the superior predictive performance on matrix completion tasks of our proposed method compared to state-of-the-art competitors, including other variants of adversarial nonnegative matrix factorization.

cs.LG↗

arXiv2021

Investigating Critical Risk Factors in Liver Cancer Prediction

We exploit liver cancer prediction model using machine learning algorithms based on epidemiological data of over 55 thousand peoples from 2014 to the present. The best performance is an AUC of 0.71. We analyzed model parameters to investigate critical risk factors that contribute the most to prediction.

cs.LG↗

arXiv2020

Li-ion Battery Fault Detection in Large Packs Using Force and Gas Sensors

Internal short circuits are a leading cause of battery thermal runaway, and hence a major safety issue for electric vehicles. An internal short circuit with low resistance is called a hard internal short, which causes a high internal current flow that leads to an extremely fast temperature rise, gas generation, cell swelling, and ultimately battery rupture and failure. Thus it is crucial to detect these faults immediately after they get triggered. In large battery packs with many cells in parallel, detecting an internal short circuit event using voltage is difficult due to suppression of the voltage signal from the faulty cell by the other healthy cells connected in parallel. In contrast, analyzing the gas composition in the pack enclosure can provide a robust single cell failure detection method. At elevated temperature, decomposition of the battery materials results in gas generation and cell swelling. The cell structure is designed to rupture at a critical gas pressure and vent the accumulated $CO_2$ gas, in order to prevent explosive forces. In this paper, we extend our previous work by combining the models of cell thermal dynamics, swelling, and $CO_2$ gas generation. In particular, we developed a fast and high confidence level detection method of hard internal short circuit events for a battery pack by measuring cell expansion force and monitoring $CO_2$ concentrations in a pack enclosure.

eess.SY↗