PyTorchKR Papers

최신 논문

총 3,358편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2506.06335

FinBERT2: A Specialized Bidirectional Encoder for Bridging the Gap in Finance-Specific Deployment of Large Language Models

In natural language processing (NLP), the focus has shifted from encoder-only tiny language models like BERT to decoder-only large language models(LLMs) such as GPT-3. However, LLMs' practical application in the financial sector has revealed three limitations: (1) LLMs often perform worse than fine-tuned BERT on discriminative tasks despite costing much higher computational resources, such as market sentiment analysis in financial reports; (2) Application on generative tasks heavily relies on retrieval augmented generation (RAG) methods to provide current and specialized information, with general retrievers showing suboptimal performance on domain-specific retrieval tasks; (3) There are additional inadequacies in other feature-based scenarios, such as topic modeling. We introduce FinBERT2, a specialized bidirectional encoder pretrained on a high-quality, financial-specific corpus of 32b tokens. This represents the largest known Chinese financial pretraining corpus for models of this parameter size. As a better backbone, FinBERT2 can bridge the gap in the financial-specific deployment of LLMs through the following achievements: (1) Discriminative fine-tuned models (Fin-Labelers) outperform other (Fin)BERT variants by 0.4%-3.3% and leading LLMs by 9.7%-12.3% on average across five financial classification tasks. (2) Contrastive fine-tuned models (Fin-Retrievers) outperform both open-source (e.g., +6.8\% avg improvement over BGE-base-zh) and proprietary (e.g., +4.2\% avg improvement over OpenAI's text-embedding-3-large) embedders across five financial retrieval tasks; (3) Building on FinBERT2 variants, we construct the Fin-TopicModel, which enables superior clustering and topic representation for financial titles. Our work revisits financial BERT models through comparative analysis with contemporary LLMs and offers practical insights for effectively utilizing FinBERT in the LLMs era.

arXiv:2504.16856

Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification

Most datasets for sentiment analysis lack context in which an opinion was expressed, often crucial for emotion understanding, and are mainly limited by a few emotion categories. Foundation large language models (LLMs) like GPT-4 suffer from over-predicting emotions and are too resource-intensive. We design an LLM-based data synthesis pipeline and leverage a large model, Mistral-7b, for the generation of training examples for more accessible, lightweight BERT-type encoder models. We focus on enlarging the semantic diversity of examples and propose grounding the generation into a corpus of narratives to produce non-repetitive story-character-centered utterances with unique contexts over 28 emotion classes. By running 700K inferences in 450 GPU hours, we contribute with the dataset of 100K contextual and also 300K context-less examples to cover both scenarios. We use it for fine-tuning pre-trained encoders, which results in several Emo Pillars models. We show that Emo Pillars models are highly adaptive to new domains when tuned to specific tasks such as GoEmotions, ISEAR, IEMOCAP, and EmoContext, reaching the SOTA performance on the first three. We also validate our dataset, conducting statistical analysis and human evaluation, and confirm the success of our measures in utterance diversification (although less for the neutral class) and context personalization, while pointing out the need for improved handling of out-of-taxonomy labels within the pipeline.

arXiv:2506.04574

Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis

We investigate the effectiveness of large language models (LLMs), including reasoning-based and non-reasoning models, in performing zero-shot financial sentiment analysis. Using the Financial PhraseBank dataset annotated by domain experts, we evaluate how various LLMs and prompting strategies align with human-labeled sentiment in a financial context. We compare three proprietary LLMs (GPT-4o, GPT-4.1, o3-mini) under different prompting paradigms that simulate System 1 (fast and intuitive) or System 2 (slow and deliberate) thinking and benchmark them against two smaller models (FinBERT-Prosus, FinBERT-Tone) fine-tuned on financial sentiment analysis. Our findings suggest that reasoning, either through prompting or inherent model design, does not improve performance on this task. Surprisingly, the most accurate and human-aligned combination of model and method was GPT-4o without any Chain-of-Thought (CoT) prompting. We further explore how performance is impacted by linguistic complexity and annotation agreement levels, uncovering that reasoning may introduce overthinking, leading to suboptimal predictions. This suggests that for financial sentiment classification, fast, intuitive "System 1"-like thinking aligns more closely with human judgment compared to "System 2"-style slower, deliberative reasoning simulated by reasoning models or CoT prompting. Our results challenge the default assumption that more reasoning always leads to better LLM decisions, particularly in high-stakes financial applications.

arXiv:2504.19590

Arabic Metaphor Sentiment Classification Using Semantic Information

In this paper, I discuss the testing of the Arabic Metaphor Corpus (AMC) [1] using newly designed automatic tools for sentiment classification for AMC based on semantic tags. The tool incorporates semantic emotional tags for sentiment classification. I evaluate the tool using standard methods, which are F-score, recall, and precision. The method is to show the impact of Arabic online metaphors on sentiment through the newly designed tools. To the best of our knowledge, this is the first approach to conduct sentiment classification for Arabic metaphors using semantic tags to find the impact of the metaphor.

arXiv:2505.24423공식 코드 · Papers with Code

MMAFFBen: A Multilingual and Multimodal Affective Analysis Benchmark for Evaluating LLMs and VLMs

Large language models and vision-language models (which we jointly call LMs) have transformed NLP and CV, demonstrating remarkable potential across various fields. However, their capabilities in affective analysis (i.e. sentiment analysis and emotion detection) remain underexplored. This gap is largely due to the absence of comprehensive evaluation benchmarks, and the inherent complexity of affective analysis tasks. In this paper, we introduce MMAFFBen, the first extensive open-source benchmark for multilingual multimodal affective analysis. MMAFFBen encompasses text, image, and video modalities across 35 languages, covering four key affective analysis tasks: sentiment polarity, sentiment intensity, emotion classification, and emotion intensity. Moreover, we construct the MMAFFIn dataset for fine-tuning LMs on affective analysis tasks, and further develop MMAFFLM-3b and MMAFFLM-7b based on it. We evaluate various representative LMs, including GPT-4o-mini, providing a systematic comparison of their affective understanding capabilities. This project is available at https://github.com/lzw108/MMAFFBen.

arXiv:2505.24701

Multi-Domain ABSA Conversation Dataset Generation via LLMs for Real-World Evaluation and Model Comparison

Aspect-Based Sentiment Analysis (ABSA) offers granular insights into opinions but often suffers from the scarcity of diverse, labeled datasets that reflect real-world conversational nuances. This paper presents an approach for generating synthetic ABSA data using Large Language Models (LLMs) to address this gap. We detail the generation process aimed at producing data with consistent topic and sentiment distributions across multiple domains using GPT-4o. The quality and utility of the generated data were evaluated by assessing the performance of three state-of-the-art LLMs (Gemini 1.5 Pro, Claude 3.5 Sonnet, and DeepSeek-R1) on topic and sentiment classification tasks. Our results demonstrate the effectiveness of the synthetic data, revealing distinct performance trade-offs among the models: DeepSeekR1 showed higher precision, Gemini 1.5 Pro and Claude 3.5 Sonnet exhibited strong recall, and Gemini 1.5 Pro offered significantly faster inference. We conclude that LLM-based synthetic data generation is a viable and flexible method for creating valuable ABSA resources, facilitating research and model evaluation without reliance on limited or inaccessible real-world labeled data.

arXiv:2505.24650

Beyond the Black Box: Interpretability of LLMs in Finance

Large Language Models (LLMs) exhibit remarkable capabilities across a spectrum of tasks in financial services, including report generation, chatbots, sentiment analysis, regulatory compliance, investment advisory, financial knowledge retrieval, and summarization. However, their intrinsic complexity and lack of transparency pose significant challenges, especially in the highly regulated financial sector, where interpretability, fairness, and accountability are critical. As far as we are aware, this paper presents the first application in the finance domain of understanding and utilizing the inner workings of LLMs through mechanistic interpretability, addressing the pressing need for transparency and control in AI systems. Mechanistic interpretability is the most intuitive and transparent way to understand LLM behavior by reverse-engineering their internal workings. By dissecting the activations and circuits within these models, it provides insights into how specific features or components influence predictions - making it possible not only to observe but also to modify model behavior. In this paper, we explore the theoretical aspects of mechanistic interpretability and demonstrate its practical relevance through a range of financial use cases and experiments, including applications in trading strategies, sentiment analysis, bias, and hallucination detection. While not yet widely adopted, mechanistic interpretability is expected to become increasingly vital as adoption of LLMs increases. Advanced interpretability tools can ensure AI systems remain ethical, transparent, and aligned with evolving financial regulations. In this paper, we have put special emphasis on how these techniques can help unlock interpretability requirements for regulatory and compliance purposes - addressing both current needs and anticipating future expectations from financial regulators globally.

arXiv:2505.22779

Predicting Human Depression with Hybrid Data Acquisition utilizing Physical Activity Sensing and Social Media Feeds

Mental disorders including depression, anxiety, and other neurological disorders pose a significant global challenge, particularly among individuals exhibiting social avoidance tendencies. This study proposes a hybrid approach by leveraging smartphone sensor data measuring daily physical activities and analyzing their social media (Twitter) interactions for evaluating an individual's depression level. Using CNN-based deep learning models and Naive Bayes classification, we identify human physical activities accurately and also classify the user sentiments. A total of 33 participants were recruited for data acquisition, and nine relevant features were extracted from the physical activities and analyzed with their weekly depression scores, evaluated using the Geriatric Depression Scale (GDS) questionnaire. Of the nine features, six are derived from physical activities, achieving an activity recognition accuracy of 95%, while three features stem from sentiment analysis of Twitter activities, yielding a sentiment analysis accuracy of 95.6%. Notably, several physical activity features exhibited significant correlations with the severity of depression symptoms. For classifying the depression severity, a support vector machine (SVM)-based algorithm is employed that demonstrated a very high accuracy of 94%, outperforming alternative models, e.g., the multilayer perceptron (MLP) and k-nearest neighbor. It is a simple approach yet highly effective in the long run for monitoring depression without breaching personal privacy.

arXiv:2505.22125

Sentiment Simulation using Generative AI Agents

Traditional sentiment analysis relies on surface-level linguistic patterns and retrospective data, limiting its ability to capture the psychological and contextual drivers of human sentiment. These limitations constrain its effectiveness in applications that require predictive insight, such as policy testing, narrative framing, and behavioral forecasting. We present a robust framework for sentiment simulation using generative AI agents embedded with psychologically rich profiles. Agents are instantiated from a nationally representative survey of 2,485 Filipino respondents, combining sociodemographic information with validated constructs of personality traits, values, beliefs, and socio-political attitudes. The framework includes three stages: (1) agent embodiment via categorical or contextualized encodings, (2) exposure to real-world political and economic scenarios, and (3) generation of sentiment ratings accompanied by explanatory rationales. Using Quadratic Weighted Accuracy (QWA), we evaluated alignment between agent-generated and human responses. Contextualized encoding achieved 92% alignment in replicating original survey responses. In sentiment simulation tasks, agents reached 81%--86% accuracy against ground truth sentiment, with contextualized profile encodings significantly outperforming categorical (p < 0.0001, Cohen's d = 0.70). Simulation results remained consistent across repeated trials (+/-0.2--0.5% SD) and resilient to variation in scenario framing (p = 0.9676, Cohen's d = 0.02). Our findings establish a scalable framework for sentiment modeling through psychographically grounded AI agents. This work signals a paradigm shift in sentiment analysis from retrospective classification to prospective and dynamic simulation grounded in psychology of sentiment formation.

arXiv:2505.18350

Task Specific Pruning with LLM-Sieve: How Many Parameters Does Your Task Really Need?

As Large Language Models (LLMs) are increasingly being adopted for narrow tasks - such as medical question answering or sentiment analysis - and deployed in resource-constrained settings, a key question arises: how many parameters does a task actually need? In this work, we present LLM-Sieve, the first comprehensive framework for task-specific pruning of LLMs that achieves 20-75% parameter reduction with only 1-5% accuracy degradation across diverse domains. Unlike prior methods that apply uniform pruning or rely on low-rank approximations of weight matrices or inputs in isolation, LLM-Sieve (i) learns task-aware joint projections to better approximate output behavior, and (ii) employs a Genetic Algorithm to discover differentiated pruning levels for each matrix. LLM-Sieve is fully compatible with LoRA fine-tuning and quantization, and uniquely demonstrates strong generalization across datasets within the same task domain. Together, these results establish a practical and robust mechanism to generate smaller performant task-specific models.

arXiv:2505.19776

Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification

Political biases encoded by LLMs might have detrimental effects on downstream applications. Existing bias analysis methods rely on small-size intermediate tasks (questionnaire answering or political content generation) and rely on the LLMs themselves for analysis, thus propagating bias. We propose a new approach leveraging the observation that LLM sentiment predictions vary with the target entity in the same sentence. We define an entropy-based inconsistency metric to encode this prediction variability. We insert 1319 demographically and politically diverse politician names in 450 political sentences and predict target-oriented sentiment using seven models in six widely spoken languages. We observe inconsistencies in all tested combinations and aggregate them in a statistically robust analysis at different granularity levels. We observe positive and negative bias toward left and far-right politicians and positive correlations between politicians with similar alignment. Bias intensity is higher for Western languages than for others. Larger models exhibit stronger and more consistent biases and reduce discrepancies between similar languages. We partially mitigate LLM unreliability in target-oriented sentiment classification (TSC) by replacing politician names with fictional but plausible counterparts.

arXiv:2505.19426

The Role of Diversity in In-Context Learning for Large Language Models

In-context learning (ICL) is a crucial capability of current large language models (LLMs), where the selection of examples plays a key role in performance. While most existing approaches focus on selecting the most similar examples to the query, the impact of diversity in example selection remains underexplored. We systematically investigate the role of diversity in in-context example selection through experiments across a range of tasks, from sentiment classification to more challenging math and code problems. Experiments on Llama-3.1, Gemma-2, and Mistral-v0.3 families of models show that diversity-aware selection methods improve performance, particularly on complex tasks like math and code, and enhance robustness to out-of-distribution queries. To support these findings, we introduce a theoretical framework that explains the benefits of incorporating diversity in in-context example selection.

arXiv:2505.19018

CrosGrpsABS: Cross-Attention over Syntactic and Semantic Graphs for Aspect-Based Sentiment Analysis in a Low-Resource Language

Aspect-Based Sentiment Analysis (ABSA) is a fundamental task in natural language processing, offering fine-grained insights into opinions expressed in text. While existing research has largely focused on resource-rich languages like English which leveraging large annotated datasets, pre-trained models, and language-specific tools. These resources are often unavailable for low-resource languages such as Bengali. The ABSA task in Bengali remains poorly explored and is further complicated by its unique linguistic characteristics and a lack of annotated data, pre-trained models, and optimized hyperparameters. To address these challenges, this research propose CrosGrpsABS, a novel hybrid framework that leverages bidirectional cross-attention between syntactic and semantic graphs to enhance aspect-level sentiment classification. The CrosGrpsABS combines transformerbased contextual embeddings with graph convolutional networks, built upon rule-based syntactic dependency parsing and semantic similarity computations. By employing bidirectional crossattention, the model effectively fuses local syntactic structure with global semantic context, resulting in improved sentiment classification performance across both low- and high-resource settings. We evaluate CrosGrpsABS on four low-resource Bengali ABSA datasets and the high-resource English SemEval 2014 Task 4 dataset. The CrosGrpsABS consistently outperforms existing approaches, achieving notable improvements, including a 0.93% F1-score increase for the Restaurant domain and a 1.06% gain for the Laptop domain in the SemEval 2014 Task 4 benchmark.

arXiv:2505.18709

Improving Bangla Linguistics: Advanced LSTM, Bi-LSTM, and Seq2Seq Models for Translating Sylheti to Modern Bangla

Bangla or Bengali is the national language of Bangladesh, people from different regions don't talk in proper Bangla. Every division of Bangladesh has its own local language like Sylheti, Chittagong etc. In recent years some papers were published on Bangla language like sentiment analysis, fake news detection and classifications, but a few of them were on Bangla languages. This research is for the local language and this particular paper is on Sylheti language. It presented a comprehensive system using Natural Language Processing or NLP techniques for translating Pure or Modern Bangla to locally spoken Sylheti Bangla language. Total 1200 data used for training 3 models LSTM, Bi-LSTM and Seq2Seq and LSTM scored the best in performance with 89.3% accuracy. The findings of this research may contribute to the growth of Bangla NLP researchers for future more advanced innovations.

arXiv:2505.16956

On Multilingual Encoder Language Model Compression for Low-Resource Languages

In this paper, we combine two-step knowledge distillation, structured pruning, truncation, and vocabulary trimming for extremely compressing multilingual encoder-only language models for low-resource languages. Our novel approach systematically combines existing techniques and takes them to the extreme, reducing layer depth, feed-forward hidden size, and intermediate layer embedding size to create significantly smaller monolingual models while retaining essential language-specific knowledge. We achieve compression rates of up to 92% with only a marginal performance drop of 2-10% in four downstream tasks, including sentiment analysis, topic classification, named entity recognition, and part-of-speech tagging, across three low-resource languages. Notably, the performance degradation correlates with the amount of language-specific data in the teacher model, with larger datasets resulting in smaller performance losses. Additionally, we conduct extensive ablation studies to identify best practices for multilingual model compression using these techniques.

arXiv:2505.16491

LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing

Large Language Models (LLMs) have rapidly become central to NLP, demonstrating their ability to adapt to various tasks through prompting techniques, including sentiment analysis. However, we still have a limited understanding of how these models capture sentiment-related information. This study probes the hidden layers of Llama models to pinpoint where sentiment features are most represented and to assess how this affects sentiment analysis. Using probe classifiers, we analyze sentiment encoding across layers and scales, identifying the layers and pooling methods that best capture sentiment signals. Our results show that sentiment information is most concentrated in mid-layers for binary polarity tasks, with detection accuracy increasing up to 14% over prompting techniques. Additionally, we find that in decoder-only models, the last token is not consistently the most informative for sentiment encoding. Finally, this approach enables sentiment tasks to be performed with memory requirements reduced by an average of 57%. These insights contribute to a broader understanding of sentiment in LLMs, suggesting layer-specific probing as an effective approach for sentiment tasks beyond prompting, with potential to enhance model utility and reduce memory requirements.

arXiv:2505.16193

An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability

The advancements in Multimodal Large Language Models (MLLMs) have enabled various multimodal tasks to be addressed under a zero-shot paradigm. This paradigm sidesteps the cost of model fine-tuning, emerging as a dominant trend in practical application. Nevertheless, Multimodal Sentiment Analysis (MSA), a pivotal challenge in the quest for general artificial intelligence, fails to accommodate this convenience. The zero-shot paradigm exhibits undesirable performance on MSA, casting doubt on whether MLLMs can perceive sentiments as competent as supervised models. By extending the zero-shot paradigm to In-Context Learning (ICL) and conducting an in-depth study on configuring demonstrations, we validate that MLLMs indeed possess such capability. Specifically, three key factors that cover demonstrations' retrieval, presentation, and distribution are comprehensively investigated and optimized. A sentimental predictive bias inherent in MLLMs is also discovered and later effectively counteracted. By complementing each other, the devised strategies for three factors result in average accuracy improvements of 15.9% on six MSA datasets against the zero-shot paradigm and 11.2% against the random ICL baseline.

arXiv:2505.16090

Can AI Read Between The Lines? Benchmarking LLMs On Financial Nuance

As of 2025, Generative Artificial Intelligence (GenAI) has become a central tool for productivity across industries. Beyond text generation, GenAI now plays a critical role in coding, data analysis, and research workflows. As large language models (LLMs) continue to evolve, it is essential to assess the reliability and accuracy of their outputs, especially in specialized, high-stakes domains like finance. Most modern LLMs transform text into numerical vectors, which are used in operations such as cosine similarity searches to generate responses. However, this abstraction process can lead to misinterpretation of emotional tone, particularly in nuanced financial contexts. While LLMs generally excel at identifying sentiment in everyday language, these models often struggle with the nuanced, strategically ambiguous language found in earnings call transcripts. Financial disclosures frequently embed sentiment in hedged statements, forward-looking language, and industry-specific jargon, making it difficult even for human analysts to interpret consistently, let alone AI models. This paper presents findings from the Santa Clara Microsoft Practicum Project, led by Professor Charlie Goldenberg, which benchmarks the performance of Microsoft's Copilot, OpenAI's ChatGPT, Google's Gemini, and traditional machine learning models for sentiment analysis of financial text. Using Microsoft earnings call transcripts, the analysis assesses how well LLM-derived sentiment correlates with market sentiment and stock movements and evaluates the accuracy of model outputs. Prompt engineering techniques are also examined to improve sentiment analysis results. Visualizations of sentiment consistency are developed to evaluate alignment between tone and stock performance, with sentiment trends analyzed across Microsoft's lines of business to determine which segments exert the greatest influence.

arXiv:2505.16386

Omni TM-AE: A Scalable and Interpretable Embedding Model Using the Full Tsetlin Machine State Space

The increasing complexity of large-scale language models has amplified concerns regarding their interpretability and reusability. While traditional embedding models like Word2Vec and GloVe offer scalability, they lack transparency and often behave as black boxes. Conversely, interpretable models such as the Tsetlin Machine (TM) have shown promise in constructing explainable learning systems, though they previously faced limitations in scalability and reusability. In this paper, we introduce Omni Tsetlin Machine AutoEncoder (Omni TM-AE), a novel embedding model that fully exploits the information contained in the TM's state matrix, including literals previously excluded from clause formation. This method enables the construction of reusable, interpretable embeddings through a single training phase. Extensive experiments across semantic similarity, sentiment classification, and document clustering tasks show that Omni TM-AE performs competitively with and often surpasses mainstream embedding models. These results demonstrate that it is possible to balance performance, scalability, and interpretability in modern Natural Language Processing (NLP) systems without resorting to opaque architectures.

arXiv:2505.14692

Sentiment Analysis in Software Engineering: Evaluating Generative Pre-trained Transformers

Sentiment analysis plays a crucial role in understanding developer interactions, issue resolutions, and project dynamics within software engineering (SE). While traditional SE-specific sentiment analysis tools have made significant strides, they often fail to account for the nuanced and context-dependent language inherent to the domain. This study systematically evaluates the performance of bidirectional transformers, such as BERT, against generative pre-trained transformers, specifically GPT-4o-mini, in SE sentiment analysis. Using datasets from GitHub, Stack Overflow, and Jira, we benchmark the models' capabilities with fine-tuned and default configurations. The results reveal that fine-tuned GPT-4o-mini performs comparable to BERT and other bidirectional models on structured and balanced datasets like GitHub and Jira, achieving macro-averaged F1-scores of 0.93 and 0.98, respectively. However, on linguistically complex datasets with imbalanced sentiment distributions, such as Stack Overflow, the default GPT-4o-mini model exhibits superior generalization, achieving an accuracy of 85.3\% compared to the fine-tuned model's 13.1\%. These findings highlight the trade-offs between fine-tuning and leveraging pre-trained models for SE tasks. The study underscores the importance of aligning model architectures with dataset characteristics to optimize performance and proposes directions for future research in refining sentiment analysis tools tailored to the SE domain.