Hsin-Hsi Chen

Sin-Han Yang, Chung-Chi Chen, Hen-Hsen Huang et al.

Fake news and misinformation spread rapidly on the Internet. How to identify it and how to interpret the identification results have become important issues. In this paper, we propose a Dual Co-Attention Network (Dual-CAN) for fake news detection, which takes news content, social media replies, and external knowledge into consideration. Our experimental results support that the proposed Dual-CAN outperforms current representative models in two benchmark datasets. We further make in-depth discussions by comparing how models work in both datasets with empirical analysis of attention weights.

Yi-Pei Chen, An-Zi Yen, Hen-Hsen Huang et al.

Lifelogging has gained more attention due to its wide applications, such as personalized recommendations or memory assistance. The issues of collecting and extracting personal life events have emerged. People often share their life experiences with others through conversations. However, extracting life events from conversations is rarely explored. In this paper, we present Life Event Dialog, a dataset containing fine-grained life event annotations on conversational data. In addition, we initiate a novel conversational life event extraction task and differentiate the task from the public event extraction or the life event extraction from other sources like microblogs. We explore three information extraction (IE) frameworks to address the conversational life event extraction task: OpenIE, relation extraction, and event extraction. A comprehensive empirical analysis of the three baselines is established. The results suggest that the current event extraction model still struggles with extracting life events from human daily conversations. Our proposed life event dialog dataset and in-depth analysis of IE frameworks will facilitate future research on life event extraction from conversations.

Chung-Chi Chen, Hiroya Takamura, Hsin-Hsi Chen

Making our research results positively impact on society and environment is one of the goals our community has been pursuing recently. Although financial technology (FinTech) is one of the popular application fields, we notice that there is no discussion on how NLP can help in FinTech for the social good. When mentioning FinTech for social good, people are talking about financial inclusion and green finance. However, the role of NLP in these directions only gets limited discussions. To fill this gap, this paper shares our idea of how we can use NLP in FinTech for social good. We hope readers can rethink the relationship between finance and NLP based on our sharing, and further join us in improving the financial literacy of individual investors and improving the supports for impact investment.

Wei-Lin Chen, Cheng-Kuang Wu, Hsin-Hsi Chen et al.

In this paper, we address the hallucination problem commonly found in natural language generation tasks. Language models often generate fluent and convincing content but can lack consistency with the provided source, resulting in potential inaccuracies. We propose a new decoding method called Fidelity-Enriched Contrastive Search (FECS), which augments the contrastive search framework with context-aware regularization terms. FECS promotes tokens that are semantically similar to the provided source while penalizing repetitiveness in the generated text. We demonstrate its effectiveness across two tasks prone to hallucination: abstractive summarization and dialogue generation. Results show that FECS consistently enhances faithfulness across various language model sizes while maintaining output diversity comparable to well-performing decoding algorithms.

Cheng-Kuang Wu, Wei-Lin Chen, Hsin-Hsi Chen

We explore the extension of chain-of-thought (CoT) prompting to medical reasoning for the task of automatic diagnosis. Motivated by doctors' underlying reasoning process, we present Diagnostic-Reasoning CoT (DR-CoT). Empirical results demonstrate that by simply prompting large language models trained only on general text corpus with two DR-CoT exemplars, the diagnostic accuracy improves by 15% comparing to standard prompting. Moreover, the gap reaches a pronounced 18% in out-domain settings. Our findings suggest expert-knowledge reasoning in large language models can be elicited through proper promptings.

Wei-Chi Wu, Sheng-Lun Wei, Hen-Hsen Huang et al.

Translation-based prompting is widely used in multilingual LLMs, yet its effectiveness varies across languages and tasks. We evaluate prompting strategies across ten languages of different resource levels and four benchmarks. Our analysis shows that no single strategy is universally optimal. Translation strongly benefits low-resource languages even when translation quality is imperfect, high-resource languages gain little, and prompt-based self-routing underperforms explicit translation. Motivated by these findings, we formulate prompting strategy selection as a learned decision problem and introduce lightweight classifiers that predict whether native or translation-based prompting is optimal for each instance. The classifiers achieve statistically significant improvements over fixed strategies across four benchmarks and generalize to unseen task formats not observed during training. Further analysis reveals that language resource level, rather than translation quality alone, determines when translation is beneficial.

Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen et al.

In the era of rapid Internet and social media platform development, individuals readily share their viewpoints online. The overwhelming quantity of these posts renders comprehensive analysis impractical. This necessitates an efficient recommendation system to filter and present significant, relevant opinions. Our research introduces a dual-pronged argument mining technique to improve recommendation system effectiveness, considering both professional and amateur investor perspectives. Our first strategy involves using the discrepancy between target and closing prices as an opinion indicator. The second strategy applies argument mining principles to score investors' opinions, subsequently ranking them by these scores. Experimental results confirm the effectiveness of our approach, demonstrating its ability to identify opinions with higher profit potential. Beyond profitability, our research extends to risk analysis, examining the relationship between recommended opinions and investor behaviors. This offers a holistic view of potential outcomes following the adoption of these recommended opinions.

Chr-Jr Chiu, Chung-Chi Chen, Hen-Hsen Huang et al.

Understanding the duration of news events' impact on the stock market is crucial for effective time-series forecasting, yet this facet is largely overlooked in current research. This paper addresses this research gap by introducing a novel dataset, the Impact Duration Estimation Dataset (IDED), specifically designed to estimate impact duration based on investor opinions. Our research establishes that pre-finetuning language models with IDED can enhance performance in text-based stock movement predictions. In addition, we juxtapose our proposed pre-finetuning task with sentiment analysis pre-finetuning, further affirming the significance of learning impact duration. Our findings highlight the promise of this novel research direction in stock movement prediction, offering a new avenue for financial forecasting. We also provide the IDED and pre-finetuned language models under the CC BY-NC-SA 4.0 license for academic use, fostering further exploration in this field.

Tsung-Hsuan Pan, Chung-Chi Chen, Hen-Hsen Huang et al.

Training large language models (LLMs) from scratch is an expensive endeavor, particularly as world knowledge continually evolves. To maintain relevance and accuracy of LLMs, model editing has emerged as a pivotal research area. While these methods hold promise, they can also produce unintended side effects. Their underlying factors and causes remain largely unexplored. This paper delves into a critical factor-question type-by categorizing model editing questions. Our findings reveal that the extent of performance degradation varies significantly across different question types, providing new insights for experimental design in knowledge editing. Furthermore, we investigate whether insights from smaller models can be extrapolated to larger models. Our results indicate discrepancies in findings between models of different sizes, suggesting that insights from smaller models may not necessarily apply to larger models. Additionally, we examine the impact of batch size on side effects, discovering that increasing the batch size can mitigate performance drops.

Yining Juan, Chung-Chi Chen, Hen-Hsen Huang et al.

In diverse professional environments, ranging from academic conferences to corporate earnings calls, the ability to anticipate audience questions stands paramount. Traditional methods, which rely on manual assessment of an audience's background, interests, and subject knowledge, often fall short - particularly when facing large or heterogeneous groups, leading to imprecision and inefficiency. While NLP has made strides in text-based question generation, its primary focus remains on academic settings, leaving the intricate challenges of professional domains, especially earnings call conferences, underserved. Addressing this gap, our paper pioneers the multi-question generation (MQG) task specifically designed for earnings call contexts. Our methodology involves an exhaustive collection of earnings call transcripts and a novel annotation technique to classify potential questions. Furthermore, we introduce a retriever-enhanced strategy to extract relevant information. With a core aim of generating a spectrum of potential questions that analysts might pose, we derive these directly from earnings call content. Empirical evaluations underscore our approach's edge, revealing notable excellence in the accuracy, consistency, and perplexity of the questions generated.

Po-Chun Chen, Hen-Hsen Huang, Hsin-Hsi Chen

Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction induction demonstrates that LLMs can infer better instructions with limited examples, existing approaches often rely on input-output pairs, where obtaining labeled answers can be difficult or costly. To address this limitation, we propose Strategy-Induct, a framework that derives task-level instructions solely from a small set of example questions without requiring labeled answers. Our approach first prompts the model to generate explicit reasoning strategies for each question, forming (strategy, question) pairs. These pairs are then used to induce a task instruction that guides reasoning. Experiments across multiple tasks and model scales demonstrate that Strategy-Induct outperforms state-of-the-art methods in question-only settings. Furthermore, we observe that jointly utilizing LLMs and Large Reasoning Models across task instruction generation and inference may lead to further performance improvements.

Po-Chun Chen, Hen-Hsen Huang, Hsin-Hsi Chen

To address the instability of unguided reasoning paths in standard Chain-of-Thought prompting, recent methods guide large language models (LLMs) by first eliciting a single reasoning strategy. However, relying on just one strategy for each question can still limit performance across diverse tasks. We propose Diverge-to-Induce Prompting (DIP), a framework that first prompts an LLM to generate multiple diverse high-level rationales for each question. Each rationale is then elaborated into a detailed, step-by-step draft plan. Finally, these draft plans are induced into a final plan. DIP enhances zero-shot reasoning accuracy without reliance on resource-intensive sampling. Experiments show that DIP outperforms single-strategy prompting, demonstrating the effectiveness of multi-plan induction for prompt-based reasoning.

Chia Cheng Chang, An-Zi Yen, Hen-Hsen Huang et al.

Since individuals may struggle to recall all life details and often confuse events, establishing a system to assist users in recalling forgotten experiences is essential. While numerous studies have proposed memory recall systems, these primarily rely on deep learning techniques that require extensive training and often face data scarcity due to the limited availability of personal lifelogs. As lifelogs grow over time, systems must also adapt quickly to newly accumulated data. Recently, large language models (LLMs) have demonstrated remarkable capabilities across various tasks, making them promising for personalized applications. In this work, we present a framework that leverages LLMs for proactive information access, integrating personal knowledge graphs to enhance the detection of access needs through a refined decision-making process. Our framework offers high flexibility, enabling the replacement of base models and the modification of fact retrieval methods for continuous improvement. Experimental results demonstrate that our approach effectively identifies forgotten events, supporting users in recalling past experiences more efficiently.

Sheng-Lun Wei, Yu-Ling Liao, Yen-Hua Chang et al.

This work presents the first systematic investigation of speech bias in multilingual MLLMs. We construct and release the BiasInEar dataset, a speech-augmented benchmark based on Global MMLU Lite, spanning English, Chinese, and Korean, balanced by gender and accent, and totaling 70.8 hours ($\approx$4,249 minutes) of speech with 11,200 questions. Using four complementary metrics (accuracy, entropy, APES, and Fleiss' $κ$), we evaluate nine representative models under linguistic (language and accent), demographic (gender), and structural (option order) perturbations. Our findings reveal that MLLMs are relatively robust to demographic factors but highly sensitive to language and option order, suggesting that speech can amplify existing structural biases. Moreover, architectural design and reasoning strategy substantially affect robustness across languages. Overall, this study establishes a unified framework for assessing fairness and robustness in speech-integrated LLMs, bridging the gap between text- and speech-based evaluation. The resources can be found at https://github.com/ntunlplab/BiasInEar.

Yu-Fei Shih, An-Zi Yen, Hen-Hsen Huang et al.

People often struggle to remember specific details of past experiences, which can lead to the need to revisit these memories. Consequently, lifelog retrieval has emerged as a crucial application. Various studies have explored methods to facilitate rapid access to personal lifelogs for memory recall assistance. In this paper, we propose a Captioning-Integrated Visual Lifelog (CIVIL) Retrieval System for extracting specific images from a user's visual lifelog based on textual queries. Unlike traditional embedding-based methods, our system first generates captions for visual lifelogs and then utilizes a text embedding model to project both the captions and user queries into a shared vector space. Visual lifelogs, captured through wearable cameras, provide a first-person viewpoint, necessitating the interpretation of the activities of the individual behind the camera rather than merely describing the scene. To address this, we introduce three distinct approaches: the single caption method, the collective caption method, and the merged caption method, each designed to interpret the life experiences of lifeloggers. Experimental results show that our method effectively describes first-person visual images, enhancing the outcomes of lifelog retrieval. Furthermore, we construct a textual dataset that converts visual lifelogs into captions, thereby reconstructing personal life experiences.

Yu-Xiang Lin, Chen-An Li, Sheng-Lun Wei et al.

Large audio-language models (LALMs) are often used in tasks that involve reasoning over ordered options. An open question is whether their predictions are influenced by the order of answer choices, which would indicate a form of selection bias and undermine their reliability. In this paper, we identify and analyze this problem in LALMs. We demonstrate that no model is immune to this bias through extensive experiments on six LALMs across three widely used benchmarks and their spoken counterparts. Shuffling the order of answer options can cause performance fluctuations of up to 24% and even change model rankings, raising concerns about the reliability of current evaluation practices. We also study permutation-based strategies and show that they can mitigate bias in most cases. Our work represents the first systematic investigation of this issue in LALMs, and we hope it raises awareness and motivates further research in this direction.

Wei-Hsiang Lin, Sheng-Lun Wei, Hen-Hsen Huang et al.

LLM-as-Judge frameworks are increasingly popular for AI evaluation, yet research findings on the relationship between models' generation and judgment abilities remain inconsistent. We investigate this relationship through systematic dataset- and instance-level analyses across 11 models and 21 diverse tasks. Despite both capabilities relying on the same underlying knowledge, our analyses reveal they are only weakly correlated, primarily due to LLMs' sensitivity to the responses being judged. To address this, we propose a self-reference-guided evaluation strategy that leverages a model's own answers as references. This approach significantly strengthens the correlation between generation and judgment abilities, offering a practical path to align these skills and providing a reliable proxy for model selection in evaluation tasks.

Tsung-Hsuan Pan, Chung-Chi Chen, Hen-Hsen Huang et al.

Model editing, the process of efficiently modifying factual knowledge in pre-trained language models, is critical for maintaining their accuracy and relevance. However, existing editing methods often introduce unintended side effects, degrading model performance in unpredictable ways. While much research has focused on improving editing algorithms, the role of the target knowledge's intrinsic properties remains a significant, underexplored factor. This paper addresses this gap by first proposing the ``Knowledge Spectrum,'' a systematic framework for categorizing knowledge based on its real-world popularity, the model's pre-edit familiarity, and the linguistic structure of the eliciting question. Our empirical analysis reveals that these characteristics are strong predictors of editing success and stability. Informed by these findings, we introduce the ``Knowledge-Diagnostic Framework,'' an adaptive strategy that tailors editing intensity to the diagnosed difficulty of a knowledge item. We demonstrate that this framework significantly improves success rates for challenging edits while optimizing computational resources. Our work provides a more comprehensive understanding of the factors governing model editing.

Yu-Min Tseng, Wei-Lin Chen, Chung-Chi Chen et al.

Textual data annotation, the process of labeling or tagging text with relevant information, is typically costly, time-consuming, and labor-intensive. While large language models (LLMs) have demonstrated their potential as direct alternatives to human annotators for general domains natural language processing (NLP) tasks, their effectiveness on annotation tasks in domains requiring expert knowledge remains underexplored. In this paper, we investigate: whether top-performing LLMs, which might be perceived as having expert-level proficiency in academic and professional benchmarks, can serve as direct alternatives to human expert annotators? To this end, we evaluate both individual LLMs and multi-agent approaches across three highly specialized domains: finance, biomedicine, and law. Specifically, we propose a multi-agent discussion framework to simulate a group of human annotators, where LLMs are tasked to engage in discussions by considering others' annotations and justifications before finalizing their labels. Additionally, we incorporate reasoning models (e.g., o3-mini) to enable a more comprehensive comparison. Our empirical results reveal that: (1) Individual LLMs equipped with inference-time techniques (e.g., chain-of-thought (CoT), self-consistency) show only marginal or even negative performance gains, contrary to prior literature suggesting their broad effectiveness. (2) Overall, reasoning models do not demonstrate statistically significant improvements over non-reasoning models in most settings. This suggests that extended long CoT provides relatively limited benefits for data annotation in specialized domains. (3) Certain model behaviors emerge in the multi-agent discussion environment. For instance, Claude 3.7 Sonnet with thinking rarely changes its initial annotations, even when other agents provide correct annotations or valid reasoning.

Sheng-Lun Wei, Cheng-Kuang Wu, Hen-Hsen Huang et al.

In this paper, we investigate the phenomena of "selection biases" in Large Language Models (LLMs), focusing on problems where models are tasked with choosing the optimal option from an ordered sequence. We delve into biases related to option order and token usage, which significantly impact LLMs' decision-making processes. We also quantify the impact of these biases through an extensive empirical analysis across multiple models and tasks. Furthermore, we propose mitigation strategies to enhance model performance. Our key contributions are threefold: 1) Precisely quantifying the influence of option order and token on LLMs, 2) Developing strategies to mitigate the impact of token and order sensitivity to enhance robustness, and 3) Offering a detailed analysis of sensitivity across models and tasks, which informs the creation of more stable and reliable LLM applications for selection problems.

Jian-Tao Huang, Chung-Chi Chen, Hen-Hsen Huang et al.

Headline generation, a key task in abstractive summarization, strives to condense a full-length article into a succinct, single line of text. Notably, while contemporary encoder-decoder models excel based on the ROUGE metric, they often falter when it comes to the precise generation of numerals in headlines. We identify the lack of datasets providing fine-grained annotations for accurate numeral generation as a major roadblock. To address this, we introduce a new dataset, the NumHG, and provide over 27,000 annotated numeral-rich news articles for detailed investigation. Further, we evaluate five well-performing models from previous headline generation tasks using human evaluation in terms of numerical accuracy, reasonableness, and readability. Our study reveals a need for improvement in numerical accuracy, demonstrating the potential of the NumHG dataset to drive progress in number-focused headline generation and stimulate further discussions in numeral-focused text generation.

Wei-Lin Chen, Cheng-Kuang Wu, Yun-Nung Chen et al.

Large language models (LLMs) have exhibited striking in-context learning (ICL) ability to adapt to target tasks with a few input-output demonstrations. For better ICL, different methods are proposed to select representative demonstrations from existing training corpora. However, such settings are not aligned with real-world practices, as end-users usually query LMs without access to demonstration pools. In this work, we introduce Self-ICL -- a simple framework which bootstraps LMs' intrinsic capabilities to perform zero-shot ICL. Given a test input, Self-ICL first prompts the model to generate pseudo-inputs. Next, the model predicts pseudo-labels for the pseudo-inputs via zero-shot prompting. Finally, we perform ICL for the test input with the pseudo-input-label pairs as demonstrations. Evaluation on 23 BIG-Bench Hard tasks shows Self-ICL outperforms zero-shot baselines on both average accuracy and head-to-head comparison. Moreover, with zero-shot chain-of-thought, Self-ICL achieves results comparable to using real demonstrations. Additionally, we conduct a range of analyses to validate Self-ICL's effectiveness and provide insights for its behaviors under different settings.

Wei-Lin Chen, An-Zi Yen, Cheng-Kuang Wu et al.

Language models (LMs) that jointly generate end-task answers as well as free-text rationales are known as self-rationalization models. Recent works demonstrate great performance gain for self-rationalization by few-shot prompting LMs with rationale-augmented exemplars. However, the ability to benefit from explanations only emerges with large-scale LMs, which have poor accessibility. In this work, we explore the less-studied setting of leveraging explanations for small LMs to improve few-shot self-rationalization. We first revisit the relationship between rationales and answers. Inspired by the implicit mental process of how human beings assess explanations, we present a novel approach, Zero-shot Augmentation of Rationale-Answer pairs (ZARA), to automatically construct pseudo-parallel data for self-training by reducing the problem of plausibility judgement to natural language inference. Experimental results show ZARA achieves SOTA performance on the FEB benchmark, for both the task accuracy and the explanation metric. In addition, we conduct human and quantitative evaluation validating ZARA's ability to automatically identify plausible and accurate rationale-answer pairs.

Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen

Opinion mining is a prevalent research issue in many domains. In the financial domain, however, it is still in the early stages. Most of the researches on this topic only focus on the coarse-grained market sentiment analysis, i.e., 2-way classification for bullish/bearish. Thanks to the recent financial technology (FinTech) development, some interdisciplinary researchers start to involve in the in-depth analysis of investors' opinions. In this position paper, we first define the financial opinions from both coarse-grained and fine-grained points of views, and then provide an overview on the issues already tackled. In addition to listing research issues of the existing topics, we further propose a road map of fine-grained financial opinion mining for future researches, and point out several challenges yet to explore. Moreover, we provide possible directions to deal with the proposed research issues.

An-Zi Yen, Hen-Hsen Huang, Hsin-Hsi Chen

With the advance of science and technology, people are used to record their daily life events via writing blogs, uploading social media posts, taking photos, or filming videos. Such rich repository personal information is useful for supporting human living assistance. The main challenge is how to store and manage personal knowledge from various sources. In this position paper, we propose a research agenda on mining personal knowledge from various sources of lifelogs, personal knowledge base construction, and information recall for assisting people to recall their experiences.

Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen

Financial Technology (FinTech) is one of the worldwide rapidly-rising topics in the past five years according to the statistics of FinTech from Google Trends. In this position paper, we focus on the researches applying natural language processing (NLP) technologies in the finance domain. Our goal is to indicate the position we are now and provide the blueprint for future researches. We go through the application scenarios from three aspects including Know Your Customer (KYC), Know Your Product (KYP), and Satisfy Your Customer (SYC). Both formal documents and informal textual data are analyzed to understand corporate customers and personal customers. Furthermore, we talk over how to dynamically update the features of products from the prospect and the risk points of view. Finally, we discuss satisfying the customers in both B2C and C2C business models. After summarizing the past and the recent challenges, we highlight several promising future research directions in the trend of FinTech and the open finance tendency.

Chung-Chi Chen, Hen-Hsen Huang, Yow-Ting Shiue et al.

Numerals that contain much information in financial documents are crucial for financial decision making. They play different roles in financial analysis processes. This paper is aimed at understanding the meanings of numerals in financial tweets for fine-grained crowd-based forecasting. We propose a taxonomy that classifies the numerals in financial tweets into 7 categories, and further extend some of these categories into several subcategories. Neural network-based models with word and character-level encoders are proposed for 7-way classification and 17-way classification. We perform backtest to confirm the effectiveness of the numeric opinions made by the crowd. This work is the first attempt to understand numerals in financial social media data, and we provide the first comparison of fine-grained opinion of individual investors and analysts based on their forecast price. The numeral corpus used in our experiments, called FinNum 1.0 , is available for research purposes.

Kuan-Yu Chen, Shih-Hung Liu, Berlin Chen et al.

Word embedding methods revolve around learning continuous distributed vector representations of words with neural networks, which can capture semantic and/or syntactic cues, and in turn be used to induce similarity measures among words, sentences and documents in context. Celebrated methods can be categorized as prediction-based and count-based methods according to the training objectives and model architectures. Their pros and cons have been extensively analyzed and evaluated in recent studies, but there is relatively less work continuing the line of research to develop an enhanced learning method that brings together the advantages of the two model families. In addition, the interpretation of the learned word representations still remains somewhat opaque. Motivated by the observations and considering the pressing need, this paper presents a novel method for learning the word representations, which not only inherits the advantages of classic word embedding methods but also offers a clearer and more rigorous interpretation of the learned word representations. Built upon the proposed word embedding method, we further formulate a translation-based language modeling framework for the extractive speech summarization task. A series of empirical evaluations demonstrate the effectiveness of the proposed word representation learning and language modeling techniques in extractive speech summarization.

Kuan-Yu Chen, Shih-Hung Liu, Hsin-Min Wang et al.

Owing to the rapidly growing multimedia content available on the Internet, extractive spoken document summarization, with the purpose of automatically selecting a set of representative sentences from a spoken document to concisely express the most important theme of the document, has been an active area of research and experimentation. On the other hand, word embedding has emerged as a newly favorite research subject because of its excellent performance in many natural language processing (NLP)-related tasks. However, as far as we are aware, there are relatively few studies investigating its use in extractive text or speech summarization. A common thread of leveraging word embeddings in the summarization process is to represent the document (or sentence) by averaging the word embeddings of the words occurring in the document (or sentence). Then, intuitively, the cosine similarity measure can be employed to determine the relevance degree between a pair of representations. Beyond the continued efforts made to improve the representation of words, this paper focuses on building novel and efficient ranking models based on the general word embedding methods for extractive speech summarization. Experimental results demonstrate the effectiveness of our proposed methods, compared to existing state-of-the-art methods.