arXiv subjects

Yangyang Yu

Publications and source records attributed to Yangyang Yu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Benchmarking nuclear energy density functionals with new mass data

Nuclear masses play a crucial role in both nuclear physics and astrophysics, driving sustained efforts toward their precise experimental determination and reliable theoretical prediction. In this work, we compile the newly measured masses for 296 nuclides from 40 references published between 2021 and 2024, subsequent to the release of the latest Atomic Mass Evaluation. These data are used to benchmark the performance of several relativistic and non-relativistic density functionals, including PC-PK1, TMA, SLy4, SV-min, UNEDF1, and the recently proposed PC-L3R. Results for PC-PK1 and PC-L3R are obtained using the state-of-the-art deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc), while the others are adopted from existing literature. It is found that the DRHBc calculations with PC-PK1 and PC-L3R achieve an accuracy better than 1.5 MeV, outperforming the other functionals, which all exhibit root-mean-square deviations exceeding 2 MeV. The odd-even effects and isospin dependence in these theoretical descriptions are examined. The PC-PK1 and PC-L3R descriptions are qualitatively similar, both exhibiting robust isospin dependence along isotopic chains. Finally, a quantitative comparison between the PC-PK1 and PC-L3R results is presented, with their largest discrepancies analyzed in terms of potential energy curves from constrained DRHBc calculations.

nucl-th↗

arXiv2025

Truth Neurons

Despite their remarkable success and deployment across diverse workflows, language models sometimes produce untruthful responses. Our limited understanding of how truthfulness is mechanistically encoded within these models jeopardizes their reliability and safety. In this paper, we propose a method for identifying representations of truthfulness at the neuron level. We show that language models contain truth neurons, which encode truthfulness in a subject-agnostic manner. Experiments conducted across models of varying scales validate the existence of truth neurons, confirming that the encoding of truthfulness at the neuron level is a property shared by many language models. The distribution patterns of truth neurons over layers align with prior findings on the geometry of truthfulness. Selectively suppressing the activations of truth neurons found through the TruthfulQA dataset degrades performance both on TruthfulQA and on other benchmarks, showing that the truthfulness mechanisms are not tied to a specific dataset. Our results offer novel insights into the mechanisms underlying truthfulness in language models and highlight potential directions toward improving their trustworthiness and reliability.

cs.CL↗

arXiv2025

Product vs. Process: Exploring EFL Students' Editing of AI-Generated Text for Expository Writing

Text generated by artificial intelligence (AI) chatbots is increasingly used in English as a foreign language (EFL) writing contexts, yet its impact on students' expository writing process and compositions remains understudied. This research examines how EFL secondary students edit AI-generated text. Exploring editing behaviors in their expository writing process and in expository compositions, and their effect on human-rated scores for content, organization, language, and overall quality. Participants were 39 Hong Kong secondary students who wrote an expository composition with AI chatbots in a workshop. A convergent design was employed to analyze their screen recordings and compositions to examine students' editing behaviors and writing qualities. Analytical methods included qualitative coding, descriptive statistics, temporal sequence analysis, human-rated scoring, and multiple linear regression analysis. We analyzed over 260 edits per dataset, and identified two editing patterns: one where students refined introductory units repeatedly before progressing, and another where they quickly shifted to extensive edits in body units (e.g., topic and supporting sentences). MLR analyses revealed that the number of AI-generated words positively predicted all score dimensions, while most editing variables showed minimal impact. These results suggest a disconnect between students' significant editing effort and improved composition quality, indicating AI supports but does not replace writing skills. The findings highlight the importance of genre-specific instruction and process-focused writing before AI integration. Educators should also develop assessments valuing both process and product to encourage critical engagement with AI text.

cs.CL↗

arXiv2025

Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim $\rightarrow$ Evidence Reasoning

Large language models (LLMs) are increasingly being used for complex research tasks such as literature review, idea generation, and scientific paper analysis, yet their ability to truly understand and process the intricate relationships within complex research papers, such as the logical links between claims and supporting evidence remains largely unexplored. In this study, we present CLAIM-BENCH, a comprehensive benchmark for evaluating LLMs' capabilities in scientific claim-evidence extraction and validation, a task that reflects deeper comprehension of scientific argumentation. We systematically compare three approaches which are inspired by divide and conquer approaches, across six diverse LLMs, highlighting model-specific strengths and weaknesses in scientific comprehension. Through evaluation involving over 300 claim-evidence pairs across multiple research domains, we reveal significant limitations in LLMs' ability to process complex scientific content. Our results demonstrate that closed-source models like GPT-4 and Claude consistently outperform open-source counterparts in precision and recall across claim-evidence identification tasks. Furthermore, strategically designed three-pass and one-by-one prompting approaches significantly improve LLMs' abilities to accurately link dispersed evidence with claims, although this comes at increased computational cost. CLAIM-BENCH sets a new standard for evaluating scientific comprehension in LLMs, offering both a diagnostic tool and a path forward for building systems capable of deeper, more reliable reasoning across full-length papers.

cs.CL↗

arXiv2025

Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications

Financial LLMs hold promise for advancing financial tasks and domain-specific applications. However, they are limited by scarce corpora, weak multimodal capabilities, and narrow evaluations, making them less suited for real-world application. To address this, we introduce \textit{Open-FinLLMs}, the first open-source multimodal financial LLMs designed to handle diverse tasks across text, tabular, time-series, and chart data, excelling in zero-shot, few-shot, and fine-tuning settings. The suite includes FinLLaMA, pre-trained on a comprehensive 52-billion-token corpus; FinLLaMA-Instruct, fine-tuned with 573K financial instructions; and FinLLaVA, enhanced with 1.43M multimodal tuning pairs for strong cross-modal reasoning. We comprehensively evaluate Open-FinLLMs across 14 financial tasks, 30 datasets, and 4 multimodal tasks in zero-shot, few-shot, and supervised fine-tuning settings, introducing two new multimodal evaluation datasets. Our results show that Open-FinLLMs outperforms afvanced financial and general LLMs such as GPT-4, across financial NLP, decision-making, and multi-modal tasks, highlighting their potential to tackle real-world challenges. To foster innovation and collaboration across academia and industry, we release all codes (https://anonymous.4open.science/r/PIXIU2-0D70/B1D7/LICENSE) and models under OSI-approved licenses.

cs.CL↗

arXiv2025

Exploring EFL Secondary Students' AI-generated Text Editing While Composition Writing

Generative Artificial Intelligence is transforming how English as a foreign language students write. Still, little is known about how students manipulate text generated by generative AI during the writing process. This study investigates how EFL secondary school students integrate and modify AI-generated text when completing an expository writing task. The study employed an exploratory mixed-methods design. Screen recordings were collected from 29 Hong Kong secondary school students who attended an AI-assisted writing workshop and recorded their screens while using generative AI to write an article. Content analysis with hierarchical coding and thematic analysis with a multiple case study approach were adopted to analyze the recordings. 15 types of AI-generated text edits across seven categories were identified from the recordings. Notably, AI-initiated edits from iOS and Google Docs emerged as unanticipated sources of AI-generated text. A thematic analysis revealed four patterns of students' editing behaviors based on planning and drafting direction: planning with top-down drafting and revising; top-down drafting and revising without planning; planning with bottom-up drafting and revising; and bottom-up drafting and revising without planning. Network graphs illustrate cases of each pattern, demonstrating that students' interactions with AI-generated text involve more complex cognitive processes than simple text insertion. The findings challenge assumptions about students' passive, simplistic use of generative AI tools and have implications for developing explicit instructional approaches to teaching AI-generated text editing strategies in the AFL writing pedagogy.

cs.CY↗

arXiv2025

RiskLabs: Predicting Financial Risk Using Large Language Model based on Multimodal and Multi-Sources Data

The integration of Artificial Intelligence (AI) techniques, particularly large language models (LLMs), in finance has garnered increasing academic attention. Despite progress, existing studies predominantly focus on tasks like financial text summarization, question-answering, and stock movement prediction (binary classification), the application of LLMs to financial risk prediction remains underexplored. Addressing this gap, in this paper, we introduce RiskLabs, a novel framework that leverages LLMs to analyze and predict financial risks. RiskLabs uniquely integrates multimodal financial data, including textual and vocal information from Earnings Conference Calls (ECCs), market-related time series data, and contextual news data to improve financial risk prediction. Empirical results demonstrate RiskLabs' effectiveness in forecasting both market volatility and variance. Through comparative experiments, we examine the contributions of different data sources to financial risk assessment and highlight the crucial role of LLMs in this process. We also discuss the challenges associated with using LLMs for financial risk prediction and explore the potential of combining them with multimodal data for this purpose.

q-fin.RM↗

arXiv2025

FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading

Large language models (LLMs) fine-tuned on multimodal financial data have demonstrated impressive reasoning capabilities in various financial tasks. However, they often struggle with multi-step, goal-oriented scenarios in interactive financial markets, such as trading, where complex agentic approaches are required to improve decision-making. To address this, we propose \textsc{FLAG-Trader}, a unified architecture integrating linguistic processing (via LLMs) with gradient-driven reinforcement learning (RL) policy optimization, in which a partially fine-tuned LLM acts as the policy network, leveraging pre-trained knowledge while adapting to the financial domain through parameter-efficient fine-tuning. Through policy gradient optimization driven by trading rewards, our framework not only enhances LLM performance in trading but also improves results on other financial-domain tasks. We present extensive empirical evidence to validate these enhancements.

cs.AI↗

arXiv2024

INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent

Recent advancements have underscored the potential of large language model (LLM)-based agents in financial decision-making. Despite this progress, the field currently encounters two main challenges: (1) the lack of a comprehensive LLM agent framework adaptable to a variety of financial tasks, and (2) the absence of standardized benchmarks and consistent datasets for assessing agent performance. To tackle these issues, we introduce \textsc{InvestorBench}, the first benchmark specifically designed for evaluating LLM-based agents in diverse financial decision-making contexts. InvestorBench enhances the versatility of LLM-enabled agents by providing a comprehensive suite of tasks applicable to different financial products, including single equities like stocks, cryptocurrencies and exchange-traded funds (ETFs). Additionally, we assess the reasoning and decision-making capabilities of our agent framework using thirteen different LLMs as backbone models, across various market environments and tasks. Furthermore, we have curated a diverse collection of open-source, multi-modal datasets and developed a comprehensive suite of environments for financial decision-making. This establishes a highly accessible platform for evaluating financial agents' performance across various scenarios.

cs.CE↗

arXiv2024

FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making

Large language models (LLMs) have demonstrated notable potential in conducting complex tasks and are increasingly utilized in various financial applications. However, high-quality sequential financial investment decision-making remains challenging. These tasks require multiple interactions with a volatile environment for every decision, demanding sufficient intelligence to maximize returns and manage risks. Although LLMs have been used to develop agent systems that surpass human teams and yield impressive investment returns, opportunities to enhance multi-sourced information synthesis and optimize decision-making outcomes through timely experience refinement remain unexplored. Here, we introduce the FinCon, an LLM-based multi-agent framework with CONceptual verbal reinforcement tailored for diverse FINancial tasks. Inspired by effective real-world investment firm organizational structures, FinCon utilizes a manager-analyst communication hierarchy. This structure allows for synchronized cross-functional agent collaboration towards unified goals through natural language interactions and equips each agent with greater memory capacity than humans. Additionally, a risk-control component in FinCon enhances decision quality by episodically initiating a self-critiquing mechanism to update systematic investment beliefs. The conceptualized beliefs serve as verbal reinforcement for the future agent's behavior and can be selectively propagated to the appropriate node that requires knowledge updates. This feature significantly improves performance while reducing unnecessary peer-to-peer communication costs. Moreover, FinCon demonstrates strong generalization capabilities in various financial tasks, including single stock trading and portfolio management.

cs.CL↗

arXiv2024

VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI

Recent advancements in Multi-modal Large Language Models (MLLMs) have opened new avenues for applications in Embodied AI. Building on previous work, EgoThink, we introduce VidEgoThink, a comprehensive benchmark for evaluating egocentric video understanding capabilities. To bridge the gap between MLLMs and low-level control in Embodied AI, we design four key interrelated tasks: video question-answering, hierarchy planning, visual grounding and reward modeling. To minimize manual annotation costs, we develop an automatic data generation pipeline based on the Ego4D dataset, leveraging the prior knowledge and multimodal capabilities of GPT-4o. Three human annotators then filter the generated data to ensure diversity and quality, resulting in the VidEgoThink benchmark. We conduct extensive experiments with three types of models: API-based MLLMs, open-source image-based MLLMs, and open-source video-based MLLMs. Experimental results indicate that all MLLMs, including GPT-4o, perform poorly across all tasks related to egocentric video understanding. These findings suggest that foundation models still require significant advancements to be effectively applied to first-person scenarios in Embodied AI. In conclusion, VidEgoThink reflects a research trend towards employing MLLMs for egocentric vision, akin to human capabilities, enabling active observation and interaction in the complex real-world environments.

cs.CV↗

arXiv2024

Single spin asymmetry $ A _{ U L } ^ { \sin ( 2 ϕ_ { h } ) }$ in dihadron production in SIDIS

The paper calculates the helicity-dependent dihadron fragmentation function (DiFF), by extending the dihadron spectator model and examine the single longitudinal spin asymmetry $A^{\sin(2ϕ_h)}_{UL}$ from dihadron in semi-inclusive inelastic scattering (SIDIS). This function elucidates the relationship between the longitudinal polarization of the fragmented quark and the transverse momentum of the resulting hadron pairs. A study by the COMPASS collaboration detected a minimal signal in their experimental search for this azimuthal asymmetry in SIDIS. Here, we use the spectator model to calculate the unknown T-odd dihadron fragmentation function $H_1^\perp$. Adopting collinear factorization to describe the data, avoiding the transverse momentum dependent factorization and the associated resummation effects, helping us understand the asymmetry and explaining why the signal is so weak. We involve the approach of transverse momentum dependence in the model calculations, in order to formulate the differential cross sections and the spin asymmetries in terms of the collinear parton distributions and the collinear DiFFs. A transverse momentum factor analysis method was used, in which the transverse momentum of the final hadron pairs was not integrated. The asymmetry of $sin(2ϕ_h)$ in COMPASS kinematics was calculated and compared with experimental data. In addition, predictions for the same asymmetry are also presented for HERMES and the Electron Ion Collider.

hep-ph↗

arXiv2024

FinBen: A Holistic Financial Benchmark for Large Language Models

LLMs have transformed NLP and shown promise in various fields, yet their potential in finance is underexplored due to a lack of comprehensive evaluation benchmarks, the rapid development of LLMs, and the complexity of financial tasks. In this paper, we introduce FinBen, the first extensive open-source evaluation benchmark, including 36 datasets spanning 24 financial tasks, covering seven critical aspects: information extraction (IE), textual analysis, question answering (QA), text generation, risk management, forecasting, and decision-making. FinBen offers several key innovations: a broader range of tasks and datasets, the first evaluation of stock trading, novel agent and Retrieval-Augmented Generation (RAG) evaluation, and three novel open-source evaluation datasets for text summarization, question answering, and stock trading. Our evaluation of 15 representative LLMs, including GPT-4, ChatGPT, and the latest Gemini, reveals several key findings: While LLMs excel in IE and textual analysis, they struggle with advanced reasoning and complex tasks like text generation and forecasting. GPT-4 excels in IE and stock trading, while Gemini is better at text generation and forecasting. Instruction-tuned LLMs improve textual analysis but offer limited benefits for complex tasks such as QA. FinBen has been used to host the first financial LLMs shared task at the FinNLP-AgentScen workshop during IJCAI-2024, attracting 12 teams. Their novel solutions outperformed GPT-4, showcasing FinBen's potential to drive innovation in financial LLMs. All datasets, results, and codes are released for the research community: https://github.com/The-FinAI/PIXIU.

cs.CL↗

arXiv2024

Nuclear mass table in deformed relativistic Hartree-Bogoliubov theory in continuum, II: Even-$Z$ nuclei

The mass table in the deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc) with the PC-PK1 density functional has been established for even-$Z$ nuclei with $8\le Z\le120$, extended from the previous work for even-even nuclei [Zhang $\it{et.~al.}$ (DRHBc Mass Table Collaboration), At. Data Nucl. Data Tables 144, 101488 (2022)]. The calculated binding energies, two-nucleon and one-neutron separation energies, root-mean-square (rms) radii of neutron, proton, matter, and charge distributions, quadrupole deformations, and neutron and proton Fermi surfaces are tabulated and compared with available experimental data. A total of 4829 even-$Z$ nuclei are predicted to be bound, with an rms deviation of 1.477 MeV from the 1244 mass data. Good agreement with the available experimental odd-even mass differences, $α$ decay energies, and charge radii is also achieved. The description accuracy for nuclear masses and nucleon separation energies as well as the prediction for drip lines is compared with the results obtained from other relativistic and nonrelativistic density functional. The comparison shows that the DRHBc theory with PC-PK1 provides an excellent microscopic description for the masses of even-$Z$ nuclei. The systematics of the nucleon separation energies, odd-even mass differences, pairing energies, two-nucleon gaps, $α$ decay energies, rms radii, quadrupole deformations, potential energy curves, neutron density distributions, and neutron mean-field potentials are discussed.

nucl-th↗

arXiv2024

Kilometer-Level Coupled Modeling Using 40 Million Cores: An Eight-Year Journey of Model Development

With current and future leading systems adopting heterogeneous architectures, adapting existing models for heterogeneous supercomputers is of urgent need for improving model resolution and reducing modeling uncertainty. This paper presents our three-week effort on porting a complex earth system model, CESM 2.2, to a 40-million-core Sunway supercomputer. Taking a non-intrusive approach that tries to minimizes manual code modifications, our project tries to achieve both improvement of performance and consistency of the model code. By using a hierarchical grid system and an OpenMP-based offloading toolkit, our porting and parallelization effort covers over 80% of the code, and achieves a simulation speed of 340 SDPD (simulated days per day) for 5-km atmosphere, 265 SDPD for 3-km ocean, and 222 SDPD for a coupled model, thus making multi-year or even multi-decadal experiments at such high resolution possible.

cs.DC↗

arXiv2023

FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design

Recent advancements in Large Language Models (LLMs) have exhibited notable efficacy in question-answering (QA) tasks across diverse domains. Their prowess in integrating extensive web knowledge has fueled interest in developing LLM-based autonomous agents. While LLMs are efficient in decoding human instructions and deriving solutions by holistically processing historical inputs, transitioning to purpose-driven agents requires a supplementary rational architecture to process multi-source information, establish reasoning chains, and prioritize critical tasks. Addressing this, we introduce \textsc{FinMem}, a novel LLM-based agent framework devised for financial decision-making. It encompasses three core modules: Profiling, to customize the agent's characteristics; Memory, with layered message processing, to aid the agent in assimilating hierarchical financial data; and Decision-making, to convert insights gained from memories into investment decisions. Notably, \textsc{FinMem}'s memory module aligns closely with the cognitive structure of human traders, offering robust interpretability and real-time tuning. Its adjustable cognitive span allows for the retention of critical information beyond human perceptual limits, thereby enhancing trading outcomes. This framework enables the agent to self-evolve its professional knowledge, react agilely to new investment cues, and continuously refine trading decisions in the volatile financial environment. We first compare \textsc{FinMem} with various algorithmic agents on a scalable real-world financial dataset, underscoring its leading trading performance in stocks. We then fine-tuned the agent's perceptual span and character setting to achieve a significantly enhanced trading performance. Collectively, \textsc{FinMem} presents a cutting-edge LLM agent framework for automated trading, boosting cumulative investment returns.

q-fin.CP↗

arXiv2023

TradingGPT: Multi-Agent System with Layered Memory and Distinct Characters for Enhanced Financial Trading Performance

Large Language Models (LLMs), prominently highlighted by the recent evolution in the Generative Pre-trained Transformers (GPT) series, have displayed significant prowess across various domains, such as aiding in healthcare diagnostics and curating analytical business reports. The efficacy of GPTs lies in their ability to decode human instructions, achieved through comprehensively processing historical inputs as an entirety within their memory system. Yet, the memory processing of GPTs does not precisely emulate the hierarchical nature of human memory. This can result in LLMs struggling to prioritize immediate and critical tasks efficiently. To bridge this gap, we introduce an innovative LLM multi-agent framework endowed with layered memories. We assert that this framework is well-suited for stock and fund trading, where the extraction of highly relevant insights from hierarchical financial data is imperative to inform trading decisions. Within this framework, one agent organizes memory into three distinct layers, each governed by a custom decay mechanism, aligning more closely with human cognitive processes. Agents can also engage in inter-agent debate. In financial trading contexts, LLMs serve as the decision core for trading agents, leveraging their layered memory system to integrate multi-source historical actions and market insights. This equips them to navigate financial changes, formulate strategies, and debate with peer agents about investment decisions. Another standout feature of our approach is to equip agents with individualized trading traits, enhancing memory diversity and decision robustness. These sophisticated designs boost the system's responsiveness to historical trades and real-time market signals, ensuring superior automated trading accuracy.

q-fin.PM↗

arXiv2023

Actively learning a Bayesian matrix fusion model with deep side information

High-dimensional deep neural network representations of images and concepts can be aligned to predict human annotations of diverse stimuli. However, such alignment requires the costly collection of behavioral responses, such that, in practice, the deep-feature spaces are only ever sparsely sampled. Here, we propose an active learning approach to adaptively sampling experimental stimuli to efficiently learn a Bayesian matrix factorization model with deep side information. We observe a significant efficiency gain over a passive baseline. Furthermore, with a sequential batched sampling strategy, the algorithm is applicable not only to small datasets collected from traditional laboratory experiments but also to settings where large-scale crowdsourced data collection is needed to accurately align the high-dimensional deep feature representations derived from pre-trained networks.

cs.AI↗