Dongji Feng

Souvika Sarkar, Dongji Feng, Shubhra Kanti Karmaker Santu

Sentence encoders have indeed been shown to achieve superior performances for many downstream text-mining tasks and, thus, claimed to be fairly general. Inspired by this, we performed a detailed study on how to leverage these sentence encoders for the "zero-shot topic inference" task, where the topics are defined/provided by the users in real-time. Extensive experiments on seven different datasets demonstrate that Sentence-BERT demonstrates superior generality compared to other encoders, while Universal Sentence Encoder can be preferred when efficiency is a top priority.

Yan Wang, Yi Han, Lingfei Qian et al.

Most recommendation benchmarks evaluate how well a model imitates user behavior. In financial advisory, however, observed actions can be noisy or short-sighted under market volatility and may conflict with a user's long-term goals. Treating what users chose as the sole ground truth, therefore, conflates behavioral imitation with decision quality. We introduce Conv-FinRe, a conversational and longitudinal benchmark for stock recommendation that evaluates LLMs beyond behavior matching. Given an onboarding interview, step-wise market context, and advisory dialogues, models must generate rankings over a fixed investment horizon. Crucially, Conv-FinRe provides multi-view references that distinguish descriptive behavior from normative utility grounded in investor-specific risk preferences, enabling diagnosis of whether an LLM follows rational analysis, mimics user noise, or is driven by market momentum. We build the benchmark from real market data and human decision trajectories, instantiate controlled advisory conversations, and evaluate a suite of state-of-the-art LLMs. Results reveal a persistent tension between rational decision quality and behavioral alignment: models that perform well on utility-based ranking often fail to match user choices, whereas behaviorally aligned models can overfit short-term noise. The dataset is publicly released on Hugging Face, and the codebase is available on GitHub.

Yi Han, Lingfei Qian, Yan Wang et al.

Large language models (LLMs) have enabled agentic systems that can reason, plan, and act across complex tasks, but it remains unclear whether they can allocate resources effectively under uncertainty. Unlike short-horizon reactive decisions, allocation requires committing scarce resources over time while balancing competing objectives and preserving flexibility for future needs. We introduce EnterpriseArena, the first benchmark for evaluating agents on long-horizon enterprise resource allocation. It instantiates CFO-style decision-making in a 132-month enterprise simulator combining firm-level financial data, anonymized business documents, macroeconomic and industry signals, and expert-validated operating rules. The environment is partially observable and reveals the state only through budgeted organizational tools, forcing agents to trade off information acquisition against conserving scarce resources. Experiments on eleven advanced LLMs show that this setting remains highly challenging: only 16% of runs survive the full horizon, and larger models do not reliably outperform smaller ones. These results identify long-horizon resource allocation under uncertainty as a distinct capability gap for current LLM agents.

Amit Das, Mostafa Rahgouy, Dongji Feng et al.

The widespread presence of hateful languages on social media has resulted in adverse effects on societal well-being. As a result, addressing this issue with high priority has become very important. Hate speech or offensive languages exist in both explicit and implicit forms, with the latter being more challenging to detect. Current research in this domain encounters several challenges. Firstly, the existing datasets primarily rely on the collection of texts containing explicit offensive keywords, making it challenging to capture implicitly offensive contents that are devoid of these keywords. Secondly, common methodologies tend to focus solely on textual analysis, neglecting the valuable insights that community information can provide. In this research paper, we introduce a novel dataset OffensiveLang, a community based implicit offensive language dataset generated by ChatGPT 3.5 containing data for 38 different target groups. Despite limitations in generating offensive texts using ChatGPT due to ethical constraints, we present a prompt-based approach that effectively generates implicit offensive languages. To ensure data quality, we evaluate the dataset with human. Additionally, we employ a prompt-based zero-shot method with ChatGPT and compare the detection results between human annotation and ChatGPT annotation. We utilize existing state-of-the-art models to see how effective they are in detecting such languages. The dataset is available here: https://github.com/AmitDasRup123/OffensiveLang

Eftekhar Hossain, Sanjeev Kumar Sinha, Naman Bansal et al.

One of the most important yet onerous tasks in the academic peer-reviewing process is composing meta-reviews, which involves assimilating diverse opinions from multiple expert peers, formulating one's self-judgment as a senior expert, and then summarizing all these perspectives into a concise holistic overview to make an overall recommendation. This process is time-consuming and can be compromised by human factors like fatigue, inconsistency, missing tiny details, etc. Given the latest major developments in Large Language Models (LLMs), it is very compelling to rigorously study whether LLMs can help metareviewers perform this important task better. In this paper, we perform a case study with three popular LLMs, i.e., GPT-3.5, LLaMA2, and PaLM2, to assist meta-reviewers in better comprehending multiple experts perspectives by generating a controlled multi-perspective summary (MPS) of their opinions. To achieve this, we prompt three LLMs with different types/levels of prompts based on the recently proposed TELeR taxonomy. Finally, we perform a detailed qualitative study of the MPSs generated by the LLMs and report our findings.

Yan Wang, Lingfei Qian, Xueqing Peng et al.

The evaluation of ranking tasks remains a significant challenge in natural language processing (NLP), particularly due to the lack of direct labels for results in real-world scenarios. Benchmark datasets play a crucial role in providing standardized testbeds that ensure fair comparisons, enhance reproducibility, and enable progress tracking, facilitating rigorous assessment and continuous improvement of ranking models. Existing NLP ranking benchmarks typically use binary relevance labels or continuous relevance scores, neglecting ordinal relevance scores. However, binary labels oversimplify relevance distinctions, while continuous scores lack a clear ordinal structure, making it challenging to capture nuanced ranking differences effectively. To address these challenges, we introduce OrdRankBen, a novel benchmark designed to capture multi-granularity relevance distinctions. Unlike conventional benchmarks, OrdRankBen incorporates structured ordinal labels, enabling more precise ranking evaluations. Given the absence of suitable datasets for ordinal relevance ranking in NLP, we constructed two datasets with distinct ordinal label distributions. We further evaluate various models for three model types, ranking-based language models, general large language models, and ranking-focused large language models on these datasets. Experimental results show that ordinal relevance modeling provides a more precise evaluation of ranking models, improving their ability to distinguish multi-granularity differences among ranked items-crucial for tasks that demand fine-grained relevance differentiation.

Wenwen Xie, Gray Gwizdz, Dongji Feng

While Large Language Models (LLMs) have emerged as promising tools for evaluating Natural Language Generation (NLG) tasks, their effectiveness is limited by their inability to appropriately weigh the importance of different topics, often overemphasizing minor details while undervaluing critical information, leading to misleading assessments. Our work proposes an efficient prompt design mechanism to address this specific limitation and provide a case study. Through strategic prompt engineering that incorporates explicit importance weighting mechanisms, we enhance using LLM-as-a-Judge ability to prioritize relevant information effectively, as demonstrated by an average improvement of 6% in the Human Alignment Rate (HAR) metric.

Leo Kampen, Carlos Rabat Villarreal, Louis Yu et al.

In this paper, we conducted a Multi-Perspective Comparative Narrative Analysis (CNA) on three prominent LLMs: GPT-3.5, PaLM2, and Llama2. We applied identical prompts and evaluated their outputs on specific tasks, ensuring an equitable and unbiased comparison between various LLMs. Our study revealed that the three LLMs generated divergent responses to the same prompt, indicating notable discrepancies in their ability to comprehend and analyze the given task. Human evaluation was used as the gold standard, evaluating four perspectives to analyze differences in LLM performance.

Chen Jiang, Kofi Osei, Sai Deepthi Yeddula et al.

Accurate precipitation forecasting is indispensable in agriculture, disaster management, and sustainable strategies. However, predicting rainfall has been challenging due to the complexity of climate systems and the heterogeneous nature of multi-source observational data, including radar, satellite imagery, and surface-level measurements. The multi-source data vary in spatial and temporal resolution, and they carry domain-specific features, making it challenging for effective integration in conventional deep learning models. Previous research has explored various machine learning techniques for weather prediction; however, most struggle with the integration of data with heterogeneous modalities. To address these limitations, we propose an Adaptive Mixture of Experts (MoE) model tailored for precipitation rate prediction. Each expert within the model specializes in a specific modality or spatio-temporal pattern. We also incorporated a dynamic router that learns to assign inputs to the most relevant experts. Our results show that this modular design enhances predictive accuracy and interpretability. In addition to the modeling framework, we introduced an interactive web-based visualization tool that enables users to intuitively explore historical weather patterns over time and space. The tool was designed to support decision-making for stakeholders in climate-sensitive sectors. We evaluated our approach using a curated multimodal climate dataset capturing real-world conditions during Hurricane Ian in 2022. The benchmark results show that the Adaptive MoE significantly outperformed all the baselines.

Amit Das, Md. Najib Hasan, Souvika Sarkar et al.

Large Language Models (LLMs) have demonstrated remarkable proficiency in generating text that closely resemble human writing. However, they often generate factually incorrect statements, a problem typically referred to as 'hallucination'. Addressing hallucination is crucial for enhancing the reliability and effectiveness of LLMs. While much research has focused on hallucinations in English, our study extends this investigation to conversational data in three languages: Hindi, Farsi, and Mandarin. We offer a comprehensive analysis of a dataset to examine both factual and linguistic errors in these languages for GPT-3.5, GPT-4o, Llama-3.1, Gemma-2.0, DeepSeek-R1 and Qwen-3. We found that LLMs produce very few hallucinated responses in Mandarin but generate a significantly higher number of hallucinations in Hindi and Farsi.

Yan Wang, Yang Ren, Lingfei Qian et al.

Accurately understanding numbers from financial reports is fundamental to how markets, regulators, algorithms, and normal people read the economy and the world, yet even with XBRL (eXtensible Business Reporting Language) designed to tag every figure with standardized accounting concepts, mapping thousands of facts to over 10,000 U.S. GAAP concepts remains costly, inconsistent, and error-prone. Existing benchmarks define tagging as flat, single-step, extreme classification over small subsets of US-GAAP concepts, overlooking both the taxonomy's hierarchical semantics and the structured nature of real tagging, where each fact must be represented as a contextualized multi-field output. These simplifications prevent fair evaluation of large language models (LLMs) under realistic reporting conditions. To address these gaps, we introduce FinTagging, the first comprehensive benchmark for structure-aware and full-scope XBRL tagging, designed to evaluate LLMs' ability to extract and align financial facts through numerical reasoning and taxonomy alignment across text and tables. We define two subtasks: FinNI for numeric identification, which extracts numerical entities and their types from XBRL reports, and FinCL for concept linking, which maps each extracted entity to the corresponding concept in the full US-GAAP taxonomy. Together, these subtasks produce a structured representation of each financial fact. We evaluate diverse LLMs under zero-shot settings and analyze their performance across both subtasks and overall tagging accuracy. Results show that LLMs generalize well in numeric identification but struggle with fine-grained concept linking, revealing current limitations in structure-aware reasoning for accurate financial disclosure. All code and datasets are available on GitHub and Hugging Face.

Zishuo Liu, Carlos Rabat Villarreal, Mostafa Rahgouy et al.

Fermi Problems (FPs) are mathematical reasoning tasks that require human-like logic and numerical reasoning. Unlike other reasoning questions, FPs often involve real-world impracticalities or ambiguous concepts, making them challenging even for humans to solve. Despite advancements in AI, particularly with large language models (LLMs) in various reasoning tasks, FPs remain relatively under-explored. This work conducted an exploratory study to examine the capabilities and limitations of LLMs in solving FPs. We first evaluated the overall performance of three advanced LLMs using a publicly available FP dataset. We designed prompts according to the recently proposed TELeR taxonomy, including a zero-shot scenario. Results indicated that all three LLMs achieved a fp_score (range between 0 - 1) below 0.5, underscoring the inherent difficulty of these reasoning tasks. To further investigate, we categorized FPs into standard and specific questions, hypothesizing that LLMs would perform better on standard questions, which are characterized by clarity and conciseness, than on specific ones. Comparative experiments confirmed this hypothesis, demonstrating that LLMs performed better on standard FPs in terms of both accuracy and efficiency.

Amit Das, Zheng Zhang, Najib Hasan et al.

Data annotation, the practice of assigning descriptive labels to raw data, is pivotal in optimizing the performance of machine learning models. However, it is a resource-intensive process susceptible to biases introduced by annotators. The emergence of sophisticated Large Language Models (LLMs) presents a unique opportunity to modernize and streamline this complex procedure. While existing research extensively evaluates the efficacy of LLMs, as annotators, this paper delves into the biases present in LLMs when annotating hate speech data. Our research contributes to understanding biases in four key categories: gender, race, religion, and disability with four LLMs: GPT-3.5, GPT-4o, Llama-3.1 and Gemma-2. Specifically targeting highly vulnerable groups within these categories, we analyze annotator biases. Furthermore, we conduct a comprehensive examination of potential factors contributing to these biases by scrutinizing the annotated data. We introduce our custom hate speech detection dataset, HateBiasNet, to conduct this research. Additionally, we perform the same experiments on the ETHOS (Mollas et al. 2022) dataset also for comparative analysis. This paper serves as a crucial resource, guiding researchers and practitioners in harnessing the potential of LLMs for data annotation, thereby fostering advancements in this critical field.

Shubhra Kanti Karmaker Santu, Dongji Feng

While LLMs have shown great success in understanding and generating text in traditional conversational settings, their potential for performing ill-defined complex tasks is largely under-studied. Indeed, we are yet to conduct comprehensive benchmarking studies with multiple LLMs that are exclusively focused on a complex task. However, conducting such benchmarking studies is challenging because of the large variations in LLMs' performance when different prompt types/styles are used and different degrees of detail are provided in the prompts. To address this issue, the paper proposes a general taxonomy that can be used to design prompts with specific properties in order to perform a wide range of complex tasks. This taxonomy will allow future benchmarking studies to report the specific categories of prompts used as part of the study, enabling meaningful comparisons across different studies. Also, by establishing a common standard through this taxonomy, researchers will be able to draw more accurate conclusions about LLMs' performance on a specific complex task.