FINANCE

FISH: A Financial Interactive System for Signal Highlighting (2023.eacl-demo)

Challenge:	a tutorial on adaptation of large language models addresses the growing demand for models that go beyond static capabilities.
Approach:	This tutorial will provide an overview of dynamic, domain-specific, and task-adaptive LLM adaptation techniques.
Outcome:	This tutorial will outline dynamic, domain-specific, and task-adaptive LLM adaptation techniques.

Copied to clipboard

Ta-wei Huang, Jia-huei Ju, Yu-shiang Huang, Cheng-wei Lin, Yi-shyuan Chiang, Chuan-ju Wang

HypoTermQA: Hypothetical Terms Dataset for Benchmarking Hallucination Tendency of LLMs (2024.eacl-srw)

Challenge:	Existing systems or studies lack interactivity and do not provide off-the-shelf signals.
Approach:	They propose an interactive system that extracts and highlights crucial financial signals . they integrate pre-trained BERT representations and a fine-tuned BERT highlighting model .
Outcome:	The proposed system extracts and highlights key financial signals efficiently and precisely.

Copied to clipboard

Cem Uluoglakci, Tugba Temizel

Equipping Language Models with Tool Use Capability for Tabular Data Analysis in Finance (2024.eacl-short)

Challenge:	Hallucinations pose a significant challenge to the reliability and alignment of Large Language Models (LLMs), limiting their widespread acceptance beyond chatbot applications.
Approach:	They propose a framework that combines benchmarking LLMs’ hallucination tendencies with efficient hallucinian detection.
Outcome:	The proposed framework provides opportunities to test and improve LLMs and can generate benchmarking datasets tailored to specific domains.

Copied to clipboard

Adrian Theuma, Ehsan Shareghi

ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Research (2025.acl-industry)

Challenge:	Large language models (LLMs) have an array of reasoning capabilities but face limitations such as error propagation and hallucination.
Approach:	They propose to use a LLAMA-2 13B CHAT model to act as a task router and task solver to offload certain reasoning steps to external tools that are more suited for the task.
Outcome:	The proposed model improves by 35.2% and 5.06% over baseline models and strong GPT-3.5 results.

Copied to clipboard

Zhiyuan Wang, Bokui Chen, Yinya Huang, Qingxing Cao, Ming He, Jianping Fan, Xiaodan Liang

CULG: Commercial Universal Language Generation (2022.naacl-industry)

Challenge:	Large Language Models (LLMs) have shown promising results in various domains, but their practical application in industry-relevant operations research presents significant challenges and opportunities.
Approach:	They propose a cognitive-inspired framework that enhances optimization through counterfactual reasoning . they use a workflow that transforms requirements into mathematical models and executable solver code .
Outcome:	Experiments show that ORMind outperforms existing methods in the NL4Opt dataset and ComplexOR dataset.

Copied to clipboard

Haonan Li, Yameng Huang, Yeyun Gong, Jian Jiao, Ruofei Zhang, Timothy Baldwin, Nan Duan

TAIL: A Toolkit for Automatic and Realistic Long-Context Large Language Model Evaluation (2024.emnlp-demo)

Challenge:	Pre-trained language models have improved performance for many NLP tasks in finance and healthcare.
Approach:	They propose a large-scale commercial universal language generation model which is pre-trained on a corpus drawn from 10 markets across 7 languages.
Outcome:	The proposed model outperforms other models on commercial generation tasks and on other markets, languages, and tasks.

Copied to clipboard

Gefei Gu, Yilun Zhao, Ruoxi Ning, Yanan Zheng, Arman Cohan

Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs (2025.acl-short)

Challenge:	Existing evaluation methods for long-context large language models are overly simplistic and require extensive human annotations.
Approach:	They propose an automatic toolkit to create realistic evaluation benchmarks . they use a document-grounded benchmark to generate question-answer pairs .
Outcome:	The proposed toolkit provides a way to create realistic evaluation benchmarks and visualize performance metrics of evaluated models.

Copied to clipboard

Megh Thakkar, Quentin Fournier, Matthew Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, Sarath Chandar

Greenback Bears and Fiscal Hawks: Finance is a Jungle and Text Embeddings Must Adapt (2024.emnlp-industry)

Challenge:	Large language models (LLMs) excel in specific technical fields, but are not explicitly trained to be safe.
Approach:	They propose a model merging-based alignment method that allows for safer domain-specific models that preserve their utility.
Outcome:	The proposed method improves safety alignment on LLMs with minimal degradation on domain-specific benchmarks.

Copied to clipboard

Peter Anderson, Mano Vikash Janardhanan, Jason He, Wei Cheng, Charlie Flanagan

Representation Learning

Challenge:	Financial documents are filled with specialized terminology, arcane jargon, and curious acronyms that pose challenges for general-purpose text embeddings.
Approach:	They propose to fine tune financial text embeddings finetuned on a carefully constructed dataset of 14.3M query-passage pairs including both public and proprietary financial documents.
Outcome:	The proposed embeddings achieve Recall@1 of 62.8% on a held-out test set, vs. only 39.2% for the best general-purpose text embeddING from OpenAI.

A Data-Centric Framework for Composable NLP Workflows (2020.emnlp-demos)

Copied to clipboard

Zhengzhong Liu, Guanxiong Ding, Avinash Bukkittu, Mansi Gupta, Pengzhi Gao, Atif Ahmed, Shikun Zhang, Xin Gao, Swapnil Singhavi, Linwei Li, Wei Wei, Zecong Hu, Haoran Shi, Xiaodan Liang, Teruko Mitamura, Eric Xing, Zhiting Hu

Challenge:	Empirical natural language processing (NLP) systems involve interoperation among multiple components . a wealth of NLP toolkits exist ( 4), such as spaCy, DKPro, CoreNLP.
Approach:	They propose a unified open-source framework that supports fast development of NLP workflows . framework includes processors for NLP tasks, visualization, and annotation .
Outcome:	The framework offers processors for NLP tasks, visualization, and annotation, and is extensible . it is delivered through two modularized yet integratable open-source projects, Forte and Stave .

BookSQL: A Large Scale Text-to-SQL Dataset for Accounting Domain (2024.naacl-long)

Copied to clipboard

Rahul Kumar, Amar Raja Dibbu, Shrutendra Harsola, Vignesh Subrahmaniam, Ashutosh Modi

Programming Languages in NLP

Challenge:	Existing models for accounting databases that can be queried using natural language are lacking in some domains.
Approach:	They propose a large-scale text-to-SQL dataset for accounting and financial domains . they propose 'bookSQl' to be used to query accounting databases using natural language .
Outcome:	The proposed model performs poorly on the existing model, pointing towards a more focused model for this domain.

Doc2EDAG: An End-to-End Document-level Framework for Chinese Financial Event Extraction (D19-1)

Copied to clipboard

Shun Zheng, Wei Cao, Wei Xu, Jiang Bian

Semantic Span Annotation: An Exploratory Study of LLM Annotation (2026.acl-srw)

Challenge:	Existing event extraction methods are limited to extract event arguments within the sentence scope.
Approach:	They propose a model which generates an entity-based directed acyclic graph to fulfill document-level EE effectively.
Outcome:	The proposed model can generate entity-based directed acyclic graph to fulfill document-level EE effectively.

Copied to clipboard

Tejas Goyal, Dhriti Krishnan, Anuj Gupta, Jaromir Savelka

CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models (2025.naacl-long)

Challenge:	Structured span extraction research is siloed by context length, annotation task, and domain . Identifying a span within a natural language text and affixing it with a semantic label has been considered a core task in NLP .
Approach:	They propose a framework for structured span annotation that integrates five datasets under a common JSONL format with character-level offsets.
Outcome:	The proposed framework can generalize across four domains under three prompting configurations.

Copied to clipboard

Ying Nie, Binwei Yan, Tianyu Guo, Hao Liu, Haoyu Wang, Wei He, Binfan Zheng, Weihao Wang, Qiang Li, Weijian Sun, Yunhe Wang, Dacheng Tao

From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines (2026.acl-industry)

Challenge:	Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging task like finance, has not been fully explored.
Approach:	They propose a benchmark to assess the financial knowledge of large language models (LLMs) in China.
Outcome:	The proposed benchmark is the most comprehensive evaluation benchmark to date for LLMs in finance.

Copied to clipboard

Sunkyung Lee, Jihye Back, Donghyeon Jeon, Soonhwan Kwon, Moonkwon Kim, Inho Kang, Jongwuk Lee

BUSTER: a “BUSiness Transaction Entity Recognition” dataset (2023.emnlp-industry)

Challenge:	Existing methods that optimize for relevance overlook document trustworthiness . Generative information retrieval (GenIR) is a promising paradigm for retrieval tasks .
Approach:	They propose an Authority-aware Generative Retriever (AuthGR) that incorporates authority into GenIR.
Outcome:	The proposed framework improves authority and accuracy in real-world user engagement and reliability.

Copied to clipboard

Andrea Zugarini, Andrew Zamai, Marco Ernandes, Leonardo Rigutini

MOROCO: The Moldavian and Romanian Dialectal Corpus (P19-1)

Challenge:	Natural Language Processing has seen major breakthroughs in the last few years, but transferring these advances into industry applications can be difficult.
Approach:	They propose to use a BUSiness Transaction Entity Recognition dataset to support industry-oriented research by exploiting both general-purpose and domain-specific language models.
Outcome:	The proposed model is the best performing model and an additional silver corpus to BUSTER.

Copied to clipboard

Andrei Butnaru, Radu Tudor Ionescu

Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in Indonesia (2025.naacl-industry)

Challenge:	Using the MOldavian and ROmanian Dialectal COrpus, we perform empirical studies on dialect identification tasks.
Approach:	They introduce the MOldavian and ROmanian Dialectal COrpus corpus which contains 33564 samples of text collected from the news domain.
Outcome:	The proposed model is based on a shallow and deep approach to discriminate between two different languages.

Copied to clipboard

Fajri Koto

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search (2025.emnlp-main)

Challenge:	Using the entire dataset, shuffling answer options introduces instability in the insurance and finance sectors.
Approach:	They propose a dataset for evaluation of performance in vocational and professional certification exams in Indonesia.
Outcome:	The proposed dataset includes 8,834 multiple-choice questions from 27 large language models across six key sectors.

Copied to clipboard

Yiming Jia, Jiachen Li, Xiang Yue, Bo Li, Ping Nie, Kai Zou, Wenhu Chen

Interpretable Company Similarity with Sparse Autoencoders (2025.acl-industry)

Challenge:	Existing vision-language models struggle with reasoning-focused tasks due to the lack of high-quality training data.
Approach:	They propose a new approach that leverages search engines to create a multimodal multimodal dataset . they use a set of 30,000 seed images to extract HTML data from 700K unique URLs .
Outcome:	The proposed model achieves the best known performance on MMMU-Pro (40.7), MathVerse (42.6), and DynaMath (55.7).

Copied to clipboard

Marco Molinari, Victor Shao, Luca Imeneo, Mateusz Mikolajczak, Abhimanyu Pandey, Vladimir Tregubiak, Sebastião Kuznetsov Ryder Torres Pereira

FINKRX: Establishing Best Practices for Korean Financial NLP (2025.acl-industry)

Challenge:	Traditionally, company comparisons rely on relative returns and discrete classifications, or a combination of both.
Approach:	They propose to use clusters of embeddings to enhance the interpretability of Large Language Models by decomposing Large Language models activations into interpretable features.
Outcome:	The proposed clusters of embeddings capture the internal representation of a company description, rather than just semantic similarity alone.

Copied to clipboard

Guijin Son, Hyunwoo Ko, Hanearl Jung, Chami Hwang

Challenge:	Existing tools to evaluate large language models in the financial domain are limited by the inherently closed nature of the financial industry.
Approach:	They present the first open leaderboard for evaluating Korean large language models focused on finance.
Outcome:	The proposed model is FINKRX, a fully open and transparent LLM built using these best practices.

Financial Sentiment Analysis: An Investigation into Common Mistakes and Silver Bullets (2020.coling-main)

Copied to clipboard

Frank Xing, Lorenzo Malandri, Yue Zhang, Erik Cambria

Sentiment Analysis

Challenge:	Recent dominance of machine learning-based natural language processing methods has overemphasized model accuracies rather than studying the reasons behind their errors.
Approach:	They investigate the error patterns of some widely acknowledged sentiment analysis methods in the finance domain.
Outcome:	The proposed models are based on the existing models and have important clues for improving them.

DisastIR: A Comprehensive Information Retrieval Benchmark for Disaster Management (2025.findings-emnlp)

Copied to clipboard

Kai Yin, Xiangjue Dong, Chengkai Liu, Lipai Huang, Yiming Xiao, Zhewei Liu, Ali Mostafavi, James Caverlee

EcoDoc: A Cost-Efficient Multimodal Document Processing System for Enterprises Using LLMs (2025.acl-industry)

Challenge:	Existing information retrieval benchmarks focus on general or specialized domains, such as medicine or finance, neglecting the unique linguistic complexity and diverse information needs encountered in disaster management scenarios.
Approach:	DisastIR is the first comprehensive IR evaluation benchmark specifically tailored for disaster management.
Outcome:	DisastIR covers 48 retrieval tasks derived from six search intents and eight general disaster categories . evaluations show no single model excelling universally .

Copied to clipboard

Ravi K. Rajendran, Biplob Debnath, Murugan Sankaradass, Srimat Chakradhar

TEN: Table Explicitization, Neurosymbolically (2026.acl-industry)

Challenge:	Recent advances in Retrieval-Augmented Generation (RAG) frameworks and Vision-Language Models (VLMs) have improved retrieval performance on multimodal documents by processing pages as images.
Approach:	They propose a cost-effective multimodal document processing system that dynamically selects the processing modalities for each page as an image or text based on page characteristics and query intent.
Outcome:	The proposed system reduces average query processing latency by 2.29 and cost by up to 10 . it reduces cost and latency while maintaining high performance on large scale deployments .

Copied to clipboard

Nikita Mehrotra, Aayush Kumar, Sumit Gulwani, Arjun Radhakrishna, Ashish Tiwari

Process Evaluation for Agentic Systems (2026.findings-eacl)

Challenge:	Existing methods for extracting tabular data from semistructured text are error-prone and costly.
Approach:	They propose a neurosymbolic approach to extract tabular data from semistructured text . TEN is a triadic feedback loop that iteratively refines table hypotheses .
Outcome:	The proposed approach outperforms neural baselines in exact match accuracy and lower hallucination rates.

Copied to clipboard

Milan Gritta, Debjit Paul, Xiaoguang Li, Lifeng Shang, Jun Wang, Gerasimos Lampouras

Challenge:	Recent adoption of LLM-based assistants has led to premature assumptions about their reliability and general capability.
Approach:	They propose to assess the feasibility of automatic process evaluation for critical applications such as medicine, finance, law and infrastructure.
Outcome:	The proposed evaluations are based on a small-scale study to assess the feasibility of automated process evaluation, present a compliance score, analyse use cases of bad and good behaviours, and offer recommendations for more holistic evaluation.

The Impact of Domain-Specific Terminology on Machine Translation for Finance in European Languages (2025.naacl-long)

Copied to clipboard

Arturo Oncevay, Charese Smiley, Xiaomo Liu

Multilinguality

Challenge:	Existing datasets for evaluating MT systems in this domain are limited.
Approach:	They propose to use a multi-parallel corpus from the European Central Bank to analyze the impact of domain-specific terminology on multilingual machine translation for finance.
Outcome:	The proposed method compares open-source multilingual MT systems with large language models (LLMs) that possess multilingual capabilities.

Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning (2026.acl-industry)

Copied to clipboard

Sanket Badhe, Deep Shah

Self-Specialization: Uncovering Latent Expertise within Large Language Models (2024.findings-acl)

Challenge:	Advanced reasoning typically requires Chain-of-Thought prompting, which is accurate but incurs prohibitive latency and substantial test-time inference costs.
Approach:	They propose to extract explicit reasoning patterns from a Teacher model and organize them into a structured list of expressive instructions for the Student model’s System Prompt.
Outcome:	Evaluated using Gemma-3 4B, the proposed model improves Macro F1 scores on StereoSet and Contract-NLI while increasing LogiQA accuracy to 70%.

Copied to clipboard

Junmo Kang, Hongyin Luo, Yada Zhu, Jacob Hansen, James Glass, David Cox, Alan Ritter, Rogerio Feris, Leonid Karlinsky

<SYNTACT>: Structuring Your Natural Language SOPs into Tailored Ambiguity-Resolved Code Templates (2025.emnlp-industry)

Challenge:	Recent studies have demonstrated the effectiveness of self-alignment in which a large language model is aligned to follow general instructions using instructional data generated from the model itself.
Approach:	They propose to use human-written seeds to align large language models to follow general instructions to achieve cross-task generalization.
Outcome:	The proposed model outperforms base models and models that are generally instruction-tuned or have been adapted to the target domain by a large margin.

Copied to clipboard

Sachin Kumar Giroh, Pushpendu Ghosh, Aryan Jain, Harshal Giridhari Paunikar, Aditi Rastogi, Promod Yenigalla, Anish Nediyanchath

Challenge:	Unstructured and ambiguous Standard Operating Procedures suffer from ambiguity, missing information, and inconsistency, all of which hinder automation.
Approach:	They propose a three-stage LLM framework that transforms unstructured SOPs into a structured plan and an executable code template.
Outcome:	The proposed framework shows an 88.4% accuracy and significant reduction in inconsistency on real-world SOPs and synthetic variants.

DS2-Instruct: Domain-Specific Data Synthesis for Large Language Models Instruction Tuning (2026.findings-eacl)

Copied to clipboard

Ruiyao Xu, Noelle I. Samia, Han Liu

FinMTEB: Finance Massive Text Embedding Benchmark (2025.emnlp-main)

Challenge:	Existing data synthesis methods focus on general-purpose tasks and fail to capture domain-specific terminology and reasoning patterns.
Approach:	They propose a framework that generates domain-specific instruction datasets without human supervision by pairing task-informed keywords with different cognitive levels from Bloom’s Taxonomy.
Outcome:	The proposed framework generates domain-specific instruction datasets without human supervision and achieves significant improvements over existing methods.

Copied to clipboard

Yixuan Tang, Yi Yang

Language Models Still Struggle to Zero-shot Reason about Time Series (2024.findings-emnlp)

Challenge:	Existing text embedding benchmarks for financial domains are inadequately addressing the nuanced requirements of specialized domains like finance.
Approach:	They propose a finance-adapted embedding model that outperforms general-purpose models . they also introduce a new model, Fin-E5, which is also open-sourced .
Outcome:	The proposed framework outperforms general-purpose models on financial embedding tasks.

Copied to clipboard

Mike Merrill, Mingtian Tan, Vinayak Gupta, Thomas Hartvigsen, Tim Althoff

FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain (2025.emnlp-main)

Challenge:	Time series are critical for decision-making in fields like finance and healthcare.
Approach:	They propose a framework for time series reasoning that includes formal tasks and a dataset of multi-scale time series paired with text captions across ten domains.
Outcome:	The proposed framework combines formal tasks and a dataset of multi-scale time series paired with text captions across ten domains to examine whether language models achieve three forms of reasoning.

Copied to clipboard

Suifeng Zhao, Zhuoran Jin, Sujian Li, Jun Gao

PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines (2025.naacl-long)

Challenge:	Existing RAG research focuses on textual data, overlooking rich visual content in financial documents.
Approach:	They propose a visual RAG benchmark tailored for finance that integrates multimodal data and provides visual citation to ensure traceability.
Outcome:	The proposed visual RAG benchmark integrates multimodal data and provides visual citation to ensure traceability.

Copied to clipboard

Reya Vir, Shreya Shankar, Harrison Chase, William Hinthorn, Aditya Parameswaran

RADO: Reasoning Audit-Driven Optimization for Rigorous Reasoning in High-Stakes Domains (2026.acl-long)

Challenge:	Large language models fail to follow instructions or meet developer expectations when running in production . a dataset of 2087 LLM pipeline prompts with 12623 assertion criteria is larger than previous collections .
Approach:	They propose a dataset of 2087 LLM pipeline prompts with 12623 assertion criteria . they fine-tuned Mistral and Llama 3 models outperform GPT-4o by 20.93% on average .
Outcome:	The proposed dataset outperforms GPT-4o and mistral models in generating assertions and offers reduced latency and improved performance.

Copied to clipboard

Zhijie Tan, Xu Chu, Guanyu Wang, Ziyu Li, Weiping Li, Tong Mo

Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements (2025.findings-acl)

Challenge:	Current reinforcement learning paradigms rely on outcome-based rewards, overlooking latent logical fallacies in intermediate steps.
Approach:	They propose a specialized audit model augmented with external tools to identify local logical ruptures and calibrate reward signals.
Outcome:	The proposed framework improves accuracy and logical rigor in high-stakes domains.

Copied to clipboard

Shu Yang, Shenzhe Zhu, Zeyu Wu, Keyu Wang, Junchi Yao, Junchao Wu, Lijie Hu, Mengdi Li, Derek F. Wong, Di Wang

Robustness in NLP

Challenge:	Existing fraud detection benchmarks focus on single-turn classification tasks, failing to capture dynamic nature of real-world fraud attempts.
Approach:	They propose a bilingual benchmark to assess LLMs' ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships.
Outcome:	The proposed model improves in role-play settings and in e-commerce and recommendation systems.

Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data (2026.eacl-long)

Copied to clipboard

Paul Quinlan, Qingguo Li, Xiaodan Zhu

Revealing the Numeracy Gap: An Empirical Investigation of Text Embedding Models (2026.findings-eacl)

Challenge:	Large language models are being rapidly applied across many fields such as healthcare, finance, transportation, and energy.
Approach:	They propose a large language model framework that integrates time-series tokens into LLMs’ vocabulary, enhancing its reasoning ability over time- and textual data.
Outcome:	The proposed framework enhances reasoning ability over time-series and textual data without compromising core natural language capabilities.

Copied to clipboard

Ningyuan Deng, Hanyu Duan, Yixuan Tang, Yi Yang

Representation Learning

Challenge:	Text embedding models are widely used in natural language processing but are often benchmarked on tasks that do not require understanding nuanced numerical information in text.
Approach:	They evaluate 13 widely used text embedding models and find they struggle to capture numerical details accurately.
Outcome:	The proposed models struggle to capture nuanced numerical details accurately, despite being benchmarked on tasks that do not require understanding nuance.

StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation (2026.acl-long)

Copied to clipboard

Huawei Zheng, Xinqi Jiang, Sen Yang, Shouling Ji, Yingcai Wu, Dazhen Deng

Constructing a Psychometric Testbed for Fair Natural Language Processing (2021.emnlp-main)

Challenge:	Domain-specific datasets of harmful prompts are scarce and often rely on manual construction. Existing efforts to improve domain knowledge and reduce harmful prompt generation are lacking.
Approach:	They propose a framework that transforms domain knowledge into actionable constraints and increases the implicitness of generated harmful prompts.
Outcome:	The proposed framework yields high-quality datasets combining strong domain relevance with implicitness, enabling more realistic red-teaming and advancing LLM safety research.

Copied to clipboard

Ahmed Abbasi, David Dobolyi, John P. Lalor, Richard G. Netemeyer, Kendall Smith, Yi Yang

FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models (2025.naacl-long)

Challenge:	Psychometric dimensions are important for understanding user behavior in various contexts including health, security, e-commerce, and finance.
Approach:	They propose to construct a corpus for psychometric natural language processing related to important dimensions such as trust, anxiety, numeracy, and literacy, in the health domain.
Outcome:	The proposed corpus includes 8,502 user-generated responses from 8,502-person survey datasets and includes self-reported demographic information, including race, sex, age, income, and education.

Copied to clipboard

Xin Guo, Haotian Xia, Zhaowei Liu, Hanyang Cao, Zhi Yang, Zhiqiang Liu, Sizhe Wang, Jinyi Niu, Chuqi Wang, Yanhui Wang, Xiaolong Liang, Xiaoming Huang, Bing Zhu, Zhongyu Wei, Yun Chen, Weining Shen, Liwen Zhang

FinTextQA: A Dataset for Long-form Financial Question Answering (2024.acl-long)

Challenge:	Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored.
Approach:	They propose to use a benchmark to evaluate large language models' financial domain knowledge and practical abilities.
Outcome:	The proposed benchmark evaluates large language models' financial domain knowledge and practical abilities.

Copied to clipboard

Jian Chen, Peilin Zhou, Yining Hua, Loh Xin, Kehui Chen, Ziyuan Li, Bing Zhu, Junwei Liang

Natural Language Interfaces

Challenge:	Existing financial question answering datasets lack scope diversity and question complexity.
Approach:	They propose to use a dataset for long-form question answering in finance to evaluate QA systems.
Outcome:	The proposed dataset includes 1,262 high-quality, source-attributed QA pairs extracted and selected from finance textbooks and government agency websites.

Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation (2026.findings-eacl)

Copied to clipboard

Minhua Lin, Zhengzhang Chen, Yanchi Liu, Xujiang Zhao, Zongyu Wu, Junxiang Wang, Xiang Zhang, Suhang Wang, Haifeng Chen

Challenge:	Time series data is ubiquitous across various domains, including manufacturing, finance, and healthcare.
Approach:	They propose a multi-agent system to generate general and domain-specific annotations for time series data.
Outcome:	The proposed system outperforms existing methods on synthetic and real-world datasets.

SILC-EFSA: Self-aware In-context Learning Correction for Entity-level Financial Sentiment Analysis (2025.coling-main)

Copied to clipboard

Senbin Zhu, ChenYuan He, Hongde Liu, Pengcheng Dong, Hanjie Zhao, Yuchen Yan, Yuxiang Jia, Hongying Zan, Min Peng

Low-Resource NLP

Challenge:	Currently, most sentiment analysis corpora use sequence-level annotation.
Approach:	They propose a two-stage approach to financial entity-level sentiment analysis called Self-aware In-context Learning Correction.
Outcome:	The proposed approach achieves state-of-the-art on the largest English and Chinese financial entity-level sentiment analysis datasets to date.

VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs (2025.emnlp-main)

Copied to clipboard

Keer Lu, Keshi Zhao, Zhuoran Zhang, Zheng Liang, Bin Cui, Tengjiao Wang, Wentao Zhang

BanFakeNews: A Dataset for Detecting Fake News in Bangla (2020.lrec-1)

Challenge:	Existing work focuses on domain-specific enhancements during fine-tuning, the challenge of which lies in catastrophic forgetting of knowledge across other domains.
Approach:	They propose a data composition framework that allows LLMs to enhance their multi-domain capabilities during supervised fine-tuning.
Outcome:	The proposed framework improves multi-domain fostering performance by 29.77% compared to uniform weights.

Copied to clipboard

Md Zobaer Hossain, Md Ashraful Rahman, Md Saiful Islam, Sudipta Kar

LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation (2025.findings-acl)

Challenge:	Impact of fake news is creating havoc worldwide.
Approach:	They propose an annotated dataset of 50K news that can be used for building automated fake news detection systems for a low resource language like Bangla.
Outcome:	The proposed system can be built with state-of-the-art NLP techniques for a low resource language like Bangla.

Copied to clipboard

Xinrui He, Yikun Ban, Jiaru Zou, Tianxin Wei, Curtiss Cook, Jingrui He

Creation and Analysis of an International Corpus of Privacy Laws (2024.lrec-main)

Challenge:	Existing frameworks for missing data imputation are lacking in a finetuning-free process and mitigating biases and uncertainty in LLM outputs.
Approach:	They propose a framework for imputation of large language models with a forest of few-shot learning LLM "trees" they use bipartite information graphs to identify relevant neighboring entries with feature and value granularity.
Outcome:	The proposed framework is based on a concept of bipartite information graphs to identify high-quality relevant neighboring entries with both feature and value granularity.

Copied to clipboard

Sonu Gupta, Geetika Gopi, Harish Balaji, Ellen Poplavska, Nora O’Toole, Siddhant Arora, Thomas Norton, Norman Sadeh, Shomir Wilson

Federated Retrieval-Augmented Generation: A Systematic Mapping Study (2025.findings-emnlp)

Challenge:	a corpus of 1,043 privacy laws, regulations, and guidelines covers 183 jurisdictions . prior efforts to study privacy law in the form of privacy policies have lacked a large-scale collection .
Approach:	They propose a corpus of 1,043 privacy laws, regulations, and guidelines covering 183 jurisdictions.
Outcome:	The Privacy Law Corpus covers 1,043 privacy laws, regulations, and guidelines covering 183 jurisdictions.

Copied to clipboard

Abhijit Chakraborty, Chahana Dahal, Vivek Gupta

AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysis (2022.emnlp-main)

Challenge:	Federated Retrieval-Augmented Generation (Federated RAG) combines Federated Learning (FL) with Retrieleval-augment Generation (RAG)
Approach:	They propose to map literature on Federated Retrieval-Augmented Generation (Federated RAG) this mapping study examines architectural patterns, temporal trends, and key challenges .
Outcome:	The proposed framework improves the factual accuracy of language models by grounding outputs in external knowledge.

Copied to clipboard

Sabyasachi Kamila, Walid Magdy, Sourav Dutta, MingXue Wang

Sentiment Analysis

Challenge:	Aspect Based Sentiment Analysis is a dominant research area with potential applications in social media analytics, business, finance, and health.
Approach:	They propose a weakly supervised multi-label Aspect Category Sentiment Analysis framework which does not use any labelled data.
Outcome:	The proposed framework outperforms weakly supervised baselines on four benchmark datasets and is able to generate multiple aspect category-sentiment pairs per review sentence.

ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering (2022.emnlp-main)

Copied to clipboard

Zhiyu Chen, Shiyang Li, Charese Smiley, Zhiqiang Ma, Sameena Shah, William Yang Wang

Natural Language Interfaces

Challenge:	Recent advances in large pre-trained language models have brought the NLP field into a new era.
Approach:	They propose a large-scale dataset to study the chain of numerical reasoning in conversational question answering.
Outcome:	The proposed dataset should push forward the exploration of real-world, complex reasoning tasks as the next research focus.

SEDAR: a Large Scale French-English Financial Domain Parallel Corpus (2020.lrec-1)

Copied to clipboard

Abbas Ghaddar, Phillippe Langlais

Multilinguality

Challenge:	Existing approaches for neural machine translation use small amount of data or monolingual data.
Approach:	They describe acquisition, preprocessing and characteristics of a large English-French parallel corpus for the financial domain.
Outcome:	The proposed corpus contains 8.6 million high quality sentence pairs . the first release of the corpus is available on github.

Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environments (2025.emnlp-main)

Copied to clipboard

Harsh Vishwakarma, Ankush Agarwal, Ojas Patil, Chaitanya Devaguptapu, Mahesh Chandran

Green & Sustainable NLP

Challenge:	Enterprise systems are crucial for enhancing productivity and strategic growth, but data is fragmented across multiple sources and access controls are complex.
Approach:	They propose a benchmark that simulates enterprise settings with 500 diverse tasks . they show that even the most capable models achieve only 41.8% task completion .
Outcome:	The proposed benchmark shows that even the most capable models achieve only 41.8% task completion.

PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance (2022.emnlp-main)

Copied to clipboard

Yang Deng, Wenqiang Lei, Wenxuan Zhang, Wai Lam, Tat-Seng Chua

Natural Language Interfaces

Challenge:	Existing studies on financial question answering systems focus on passively responding to user queries.
Approach:	They propose a new dataset to facilitate conversational question answering over hybrid contexts in finance . they propose PACIFIC to combine clarification question generation and CQA .
Outcome:	The proposed method performs multi-task learning over all sub-tasks in PACIFIC . it incorporates a simple ensemble strategy to alleviate error propagation issue .

The State of Relation Extraction Data Quality: Is Bigger Always Better? (2024.findings-acl)

Copied to clipboard

Erica Cai, Brendan O’Connor

Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection (2026.findings-acl)

Challenge:	Relation extraction (RE) methods extract tuples of relationships from text . many datasets with frequent label errors have been used .
Approach:	They review recent surveys and a sample of recent RE methods papers . they find that real-time evaluations of RE methods are possible .
Outcome:	a sample of 38 datasets currently being used shows that many have frequent label errors . a small number of relations in specific domains can more realistically evaluate methods .

Copied to clipboard

Zhiwei Liu, Yupeng Cao, Yuechen Jiang, Mohsinul Kabir, Polydoros Giannouris, Chen Xu, Ziyang Xu, Tianlei Zhu, Md. Tariquzzaman, Triantafillos Papadopoulos, Yan Wang, Lingfei Qian, Xueqing Peng, Zhuohan Xie, Ye Yuan, Saeed Almheiri, Abdulrazzaq Alnajjar, Ming-Bin Chen, Harry Stuart, Paul Thompson, Prayag Tiwari, Alejandro Lopez-Lira, Xue Liu, Jimin Huang, Sophia Ananiadou

IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval (2025.naacl-long)

Challenge:	Existing research on LLM biases has focused on direct questioning or general-purpose settings . pronounced behavioral biase despite their growing deployment in financial analysis, forecasting, and decision support.
Approach:	They propose a benchmark to evaluate behavioral biases of large language models in MFMD . they use a multilingual financial misinformation dataset to integrate these with misinformation claims .
Outcome:	The proposed benchmark evaluates behavioral biases of large language models across economic scenarios.

Copied to clipboard

Tingyu Song, Guo Gan, Mingsheng Shang, Yilun Zhao

Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training (2025.emnlp-main)

Challenge:	Current information retrieval systems struggle to handle complex instructions, despite its critical importance . current models struggle to follow complex instructions in real-world applications, resulting in user-specific tasks.
Approach:	They propose a benchmark to evaluate instruction-following information retrieval in expert domains.
Outcome:	The proposed method improves on existing models and provides valuable insights to guide future advancements in retrieval.

Copied to clipboard

Yao-Ching Yu, Tsun-Han Chiang, Cheng-Wei Tsai, Chien-Ming Huang, Wen-Kwang Tsao

A Graph-Based Method for Unsupervised Knowledge Discovery from Financial Texts (2022.lrec-1)

Challenge:	Large Language Models (LLMs) have shown remarkable advancements in specialized fields such as finance, law, and medicine.
Approach:	They propose to provide datasets covering all major training stages including pretraining, instruction fine-tuning, and reasoning distillation with cybersecurity-specific self-reflection data.
Outcome:	Extensive ablation studies show that LLMs acquire their knowledge during pretraining, while reasoning distillation leads to a 15% gain in security certification (CISSP).

Copied to clipboard

Joel Oksanen, Abhilash Majumder, Kumar Saunack, Francesca Toni, Arun Dhondiyal

Structured Data in NLP

Challenge:	A financial analyst's work involves manually reviewing lengthy filings and financial news articles in order to extract relevant pieces of information.
Approach:	They propose an end-to-end, fully unsupervised method for knowledge discovery from financial texts that integrates existing resources to construct a knowledge graph of companies and related entities.
Outcome:	The proposed method calculates the environmental rating for companies in the S&P 500 based on company filings with the SEC and provides an independent assessment of its outputs with an independent MSCI source.

InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance (2024.emnlp-main)

Copied to clipboard

Pengyu Wang, Dong Zhang, Linyang Li, Chenkun Tan, Xinghao Wang, Mozhi Zhang, Ke Ren, Botian Jiang, Xipeng Qiu

SplitThenMerge: Token-Level Skill-Compositional Sparse Mixture-of-Experts for Complex Domain-Specific Tasks (2026.findings-acl)

Challenge:	Existing methods for enhancing harmlessness and helpfulness of large language models (LLMs) involve complex and resource-intensive training processes.
Approach:	They propose a method that decouples harmlessness from helpfulness during inference phase.
Outcome:	The proposed method significantly reduces the attack success rate (ASR) of harmful instructions and jailbreak instructions while maintaining almost unchanged performance in downstream tasks.

Copied to clipboard

Yuting Huang, Jiawen Zhang, Yiquan Wu, Yinghao Hu, Fei Wu, Kun Kuang

Challenge:	Existing domain adaptation methods train heterogeneous skills together, making it difficult to reliably coordinate multiple skills when solving complex tasks.
Approach:	They propose a framework that decomposes domain competence into atomic skills and composes them dynamically during generation.
Outcome:	The proposed framework decomposes domain competence into atomic skills, trains them independently, and composes them dynamically during generation.

Federated Document-Level Biomedical Relation Extraction with Localized Context Contrast (2024.lrec-main)

Copied to clipboard

Yan Xiao, Yaochu Jin, Kuangrong Hao

DictDis: Dictionary Constrained Disambiguation for Improved NMT (2024.findings-emnlp)

Challenge:	Existing studies on relation extraction focus on document-level training without sharing raw medical texts.
Approach:	They propose a federated framework for relation extraction that enables collaborative training without sharing raw medical texts.
Outcome:	The proposed framework extends document-level relation extraction to a federated environment.

Copied to clipboard

Ayush Maheshwari, Preethi Jyothi, Ganesh Ramakrishnan

Multilinguality

Challenge:	Existing approaches to domain-specific neural machine translation (NMT) are lexically constrained and draw from domain- specific dictionaries.
Approach:	They propose a lexically constrained neural machine translation system that disambiguates between multiple dictionary candidates.
Outcome:	The proposed system disambiguates between multiple candidate translations derived from dictionaries on English-Hindi, English-German, and English-French datasets.

FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning (2026.acl-long)

Copied to clipboard

Zhuohan Xie, Daniil Orel, Rushil Thareja, Dhruv Sahnan, Hachem Madmoun, Fan Zhang, Debopriyo Banerjee, Georgi Nenkov Georgiev, Xueqing Peng, Lingfei Qian, Jimin Huang, Jinyan Su, Aaryamonvikram Singh, Rui Xing, Rania Elbadry, Chen Xu, Haonan Li, Fajri Koto, Ivan Koychev, Tanmoy Chakraborty, Yuxia Wang, Salem Lahlou, Veselin Stoyanov, Sophia Ananiadou, Preslav Nakov

Guillaume Becquin, Saher Esmeir

Challenge:	Existing benchmarks emphasize final numerical answers while neglecting intermediate reasoning steps.
Approach:	They propose a symbolic benchmark for verifiable Chain-of-Thought evaluation in finance . FINCHAIN spans 58 topics across 12 financial domains and three difficulty levels .
Outcome:	The proposed benchmark aims to bridge symbolic reasoning and factual verification.

Copied to clipboard

FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios (2026.findings-acl)

Challenge:	Existing methods to estimate covariance matrix relied on historical price data and ignored company fundamental data.
Approach:	They propose to use semantic similarity to improve covariance estimations by using a shrinkage target.
Outcome:	The proposed method is compared with the prior art estimate for covariance shrinkage using semantic similarity and price history.

Copied to clipboard

Yutao Hou, Yihan Jiang, Yuhan Xie, Jian Yang, Liwen Zhang, Hailiang Huang, Guanhua Chen, Yun Chen

Numbers Matter! Bringing Quantity-awareness to Retrieval Systems (2024.findings-emnlp)

Challenge:	Existing large language models (LLMs) are prone to misuse and misinformation, posing serious compliance risks.
Approach:	They propose a bilingual red-teaming benchmark to test an LLM’s refusal of requests that violate financial compliance.
Outcome:	The proposed benchmark is based on real-world financial crime cases and ethical violations and includes 14 subcategories covering financial crimes and ethical breaches.

Copied to clipboard

Satya Almasian, Milena Bruseva, Michael Gertz

FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval (2026.findings-acl)

Challenge:	Quantitative information is important for understanding documents and interpreting them.
Approach:	They propose two quantity-aware ranking techniques that rank both quantity and textual content . they use available retrieval systems to incorporate quantity information into queries .
Outcome:	The proposed methods can rank both quantity and textual content, either jointly or independently.

Copied to clipboard

Caishuang Huang, Yang Qiao, Rongyu Zhang, Junjie Ye, Pu Lu, null Wuwenxi, Meng Zhou, Xiku Du, Qi Zhang, Tao Gui, Xuanjing Huang

Dialogue Systems & Conversational Agents

Challenge:	Existing data synthesis methods rely on static tools to generate queries . this approach fails to capture the implicit, event-driven nature of real-world needs .
Approach:	They propose a forward synthesis framework to generate high-quality financial dialogues . they construct a repository of 43,066 tools and synthesize over 148k dialogue instances .
Outcome:	Experiments show that models trained on FinToolSyn achieve a 21.06% improvement . the framework is designed to generate high-quality financial dialogues .

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

CQE: A Comprehensive Quantity Extractor (2023.emnlp-main)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Satya Almasian, Vivian Kazakova, Philipp Göldner, Michael Gertz

A Survey of Deep Learning for Mathematical Reasoning (2023.acl-long)

Challenge:	Quantities are essential in documents to describe factual information.
Approach:	They propose a comprehensive quantity extraction framework that detects combinations of values and units, the behavior of a quantity and the concept a quantity is associated with.
Outcome:	The proposed framework outperforms existing methods and is the first to detect concepts associated with identified quantities.

Copied to clipboard

Pan Lu, Liang Qiu, Wenhao Yu, Sean Welleck, Kai-Wei Chang

The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis (2023.emnlp-main)

Challenge:	a survey of deep learning for mathematical reasoning examines the field . a comprehensive reading list is provided to assist readers interested in the field.
Approach:	They present a survey of deep learning for mathematical reasoning over the past decade . they outline directions for future research and highlight potential for further exploration .
Outcome:	The proposed framework is based on the results of a decade-long survey of deep learning for mathematical reasoning.

Copied to clipboard

Pranav Venkit, Mukund Srinath, Sanjana Gautam, Saranya Venkatraman, Vipul Gupta, Rebecca Passonneau, Shomir Wilson

Sentiment Analysis

Challenge:	Existing research reveals a notable absence of interdisciplinary endeavors to comprehend the social dimensions of sentiment analysis, encompassing aspects like emotion and fairness.
Approach:	They propose an ethics sheet encompassing critical inquiries to guide practitioners in ensuring equitable utilization of SA.
Outcome:	The proposed ethics sheet outlines the importance of adopting an interdisciplinary approach to defining sentiment in SA and offers a pragmatic solution for its implementation.

Hierarchical Retrieval with Evidence Curation for Open-Domain Financial Question Answering on Standardized Documents (2025.findings-acl)

Copied to clipboard

Jaeyoung Choe, Jihoon Kim, Woohwan Jung

Large Language Models as Financial Data Annotators: A Study on Effectiveness and Efficiency (2024.lrec-main)

Challenge:	standardized documents share similar formats and table structures . this similarity forces traditional RAG methods to misidentify near-duplicate text .
Approach:	They propose a hierarchical retrieval framework that performs hierarchically to reduce confusion among similar texts.
Outcome:	The proposed framework reduces confusion among similar documents by removing irrelevant passages . it generates complementary queries to collect missing information .

Copied to clipboard

Toyin D. Aguda, Suchetha Siddagangappa, Elena Kochkina, Simerjot Kaur, Dongsheng Wang, Charese Smiley

Temporal Referential Consistency: Do LLMs Favor Sequences Over Absolute Time References? (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable performance in data annotation tasks on general domain datasets, but their effectiveness on domain specific datasets remains under-explored.
Approach:	They compare the annotations produced by three LLMs against expert annotators and crowdworkers.
Outcome:	The proposed models outperform expert crowdworkers and crowd-sourced annotators on domain specific datasets.

Copied to clipboard

Ashutosh Bajpai, Tanmoy Chakraborty

DecisionFlow: Advancing Large Language Model as Principled Decision Maker (2025.findings-emnlp)

Challenge:	Existing efforts to ensure temporal consistency in large language models are lacking in time-sensitive fields . temporal reasoning is essential for time- sensitive fields such as finance and healthcare . a new benchmark aims to improve temporal referent consistency of LLMs .
Approach:	They propose a temporal referential consistency benchmark with a resource TEMP-ReCon to assess LLMs across temporal references.
Outcome:	The proposed model improves LLMs' temporal consistency by comparing them to baseline models.

Copied to clipboard

Xiusi Chen, Shanyong Wang, Cheng Qian, Hongru Wang, Peixuan Han, Heng Ji

Large Language Model Agents in Finance: A Survey Bridging Research, Practice, and Real-World Deployment (2025.findings-emnlp)

Challenge:	Current language models lack the structured deliberation needed for high-stakes tasks such as healthcare and finance.
Approach:	They propose a decision-making framework that guides models to reason over structured representations of actions, attributes, and constraints.
Outcome:	The proposed framework achieves up to 30% accuracy gains over strong prompting baselines and enhances alignment in outcomes.

Copied to clipboard

Yifei Dong, Fengyi Wu, Kunlin Zhang, Yilong Dai, Sanjian Zhang, Wanghao Ye, Sihan Chen, Zhi-Qi Cheng

ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions (2024.findings-emnlp)

Challenge:	a systematic review of large language models (LLMs) is conducted to better align their capabilities with real-world demands.
Approach:	They propose a functional taxonomy mapping financial domains to tasks, datasets, and institutional constraints. they catalog over 30 financial benchmarks and 20 representative models.
Outcome:	The proposed model frameworks are bridging financial practice and LLM research.

Copied to clipboard

Chan Young Park, Shuyue Stella Li, Hayoung Jung, Svitlana Volkova, Tanu Mitra, David Jurgens, Yulia Tsvetkov

Challenge:	VALUESCOPE is a framework that quantifies social norms and values within online communities.
Approach:	They propose a framework that uses language models to quantify social norms and values within online communities.
Outcome:	The proposed framework delineates differences in social norms and tracks evolution of norms in online communities and influence of significant external events like the U.S. presidential elections and the emergence of new sub-communities.

Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism (2026.acl-long)

Copied to clipboard

Yuhua Jiang, Shuang Cheng, Yihao Liu, Ermo Hua, Che Jiang, Weigao Sun, Yu Cheng, Feifei Gao, Biqing Qi, Bowen Zhou

Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data (2023.findings-emnlp)

Challenge:	Existing models lack task-guided specialized memory mechanisms . specialized generalist models excel at general language tasks but struggle in specialized domains.
Approach:	They propose a specialized generalist model with specialized memory and updater that can optimize for specialized domains.
Outcome:	The proposed model matches or surpasses baselines on general benchmarks and achieves lowest perplexity across specialized domains.

Copied to clipboard

Mubashara Akhtar, Abhilash Shankarampeta, Vivek Gupta, Arpit Patil, Oana Cocarascu, Elena Simperl

Evaluating Parameter-Efficient Finetuning Approaches for Pre-trained Models on the Financial Domain (2023.findings-emnlp)

Challenge:	Recent benchmarks have assessed language models' numerical abilities . limitations include tokenization and representation of numbers in text, hallucination, and a lack of numerical commonsense knowledge.
Approach:	They propose a hierarchical taxonomy for numerical reasoning skills that includes representation, number sense, manipulation, and complex reasoning.
Outcome:	The proposed model outperforms other models on the tabular Natural Language Inference task.

Copied to clipboard

Isabella Olariu, Cedric Lothritz, Jacques Klein, Tegawendé Bissyandé, Siwen Guo, Shohreh Haddadan

Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation? (2024.emnlp-main)

Challenge:	Large-scale language models with millions, billions, or trillions of trainable parameters are becoming increasingly popular.
Approach:	They compare performance of financial BERT-like models to their fully fine-tuned counterparts by using parameter-efficient tuning methods.
Outcome:	The proposed approaches match full fine-tuning performance on common NLP tasks, but are less studied in finance.

Copied to clipboard

Wataru Hashimoto, Hidetaka Kamigaito, Taro Watanabe

GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models (2026.acl-long)

Challenge:	Named Entity Recognition (NER) is a key task in NLP to find mentions of named entities and classify them into predefined categories.
Approach:	They investigated the impact of data augmentation on confidence calibration and uncertainty estimation in Named Entity Recognition (NER) tasks.
Outcome:	The data augmentation improves calibration and uncertainty in cross-genre and cross-lingual setting, especially in-domain setting.

Copied to clipboard

Zhaohan Zhang, Ziquan Liu, Ioannis Patras

ChartLens: Fine-grained Visual Attribution in Charts (2025.acl-long)

Challenge:	Existing methods for assessing the reliability of Large Language Models (LLMs) by confidence elicitation require expensive computational overhead or suffer from poor calibration, making them unreliable for real-world deployment.
Approach:	They propose a Generative Approach to Confidence Elicitation that enables reliable confidence elicitation for Large Language Models.
Outcome:	The proposed method achieves the best discriminative capacity and calibration on open-ended tasks without resorting to additional sampling or an auxiliary model.

Copied to clipboard

Manan Suri, Puneet Mathur, Nedim Lipka, Franck Dernoncourt, Ryan A. Rossi, Dinesh Manocha

Small Changes, Big Impact: How Manipulating a Few Neurons Can Drastically Alter LLM Aggression (2025.acl-long)

Challenge:	MLLMs suffer from hallucinations, where generated text fails to align with visual inputs.
Approach:	They propose a chart attribution algorithm that uses segmentation-based techniques to identify chart objects and employs set-of-marks prompting with MLLMs for fine-grained visual attribution.
Outcome:	The proposed algorithm improves fine-grained attributions by 26-66% .

Copied to clipboard

Jaewook Lee, Junseo Jang, Oh-Woog Kwon, Harksoo Kim

Challenge:	Recent advances in Large Language Models have led to innovations in various domains such as education, healthcare, and finance, while raising serious concerns that they can be easily misused for malicious purposes.
Approach:	They identify specific neurons (“aggression neurons”) closely related to the expression of aggression and analyze how manipulating them affects the model’s overall aggression.
Outcome:	The proposed model outputs show that manipulating neurons can increase aggression by up to 33% in all models and even more extreme when they are concentrated in certain layers.

Financial Language Model Evaluation (FLaME) (2025.findings-acl)

Copied to clipboard

Glenn Matlin, Mika Okamoto, Huzaifa Pardawala, Yang Yang, Sudheer Chava

Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models (2024.emnlp-main)

Challenge:	Language Models (LMs) have demonstrated impressive capabilities with core NLP tasks in finance, but their effectiveness is difficult to assess due to gaps in evaluation methodologies.
Approach:	They propose to use a framework to evaluate language models against ‘reasoning-reinforced’ LMs to measure their performance on finance NLP tasks.
Outcome:	The proposed frameworks are open-source and provide data and data for the study.

Copied to clipboard

Jiaxin Zhang, Wendi Cui, Yiran Huang, Kamalika Das, Sricharan Kumar

Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmark (2024.emnlp-main)

Challenge:	Large language models capture factual knowledge across a wide range of domains, but refining their capabilities on previously seen knowledge remains a challenge.
Approach:	They propose a synthetic knowledge ingestion method that leverages fine-grained synthesis and interleaved generation to construct high-quality data representations from raw knowledge sources.
Outcome:	The proposed method outperforms baseline methods on question-answering tasks spanning finance, biomedicine, and open-generation domains.

Copied to clipboard

Elizabeth Fons, Rachneet Kaur, Soham Palande, Zhen Zeng, Tucker Balch, Manuela Veloso, Svitlana Vyetrenko

Dense Retrieval with Quantity Comparison Intent (2025.findings-acl)

Challenge:	Large Language Models (LLMs) are a critical tool for time series analysis and reporting in many fields, including healthcare, finance, climate, and many more.
Approach:	They propose a framework for rigorously evaluating the capabilities of Large Language Models (LLMs) on time series understanding, encompassing both univariate and multivariate forms.
Outcome:	The proposed framework delineates various characteristics inherent in time series data.

Copied to clipboard

Prayas Agrawal, Nandeesh Kumar K M, Muthusamy Chelliah, Surender Kumar, Soumen Chakrabarti

Are LLMs Rational Investors? A Study on the Financial Bias in LLMs (2025.findings-acl)

Challenge:	Existing sparse and dense retrieval systems fragment numerals and units that express quantities in arbitrary ways.
Approach:	They propose a dense retrieval system built around a density multi-vector index . they propose eliciting and exploiting quantities and associated comparison intents .
Outcome:	The proposed system is faster and more accurate than popular PLMs on two public and one proprietary e-commerce benchmarks.

Copied to clipboard

Yuhang Zhou, Yuchen Ni, Zhiheng Xi, Zhangyue Yin, Yu He, Gan Yunhui, Xiang Liu, Zhang Jian, Sen Liu, Xipeng Qiu, Yixin Cao, Guangnan Ye, Hongfeng Chai

Source-free Domain Adaptation for Aspect-based Sentiment Analysis (2024.lrec-main)

Challenge:	Existing studies on biases within specific domains, such as finance, remain limited.
Approach:	They propose a framework to detect, detect, analyze and mitigate financial biases in large language models.
Outcome:	The proposed framework reduces bias by 68% for the most biased model, according to key metrics.

Copied to clipboard

Zishuo Zhao, Ziyang Ma, Zhenzhou Lin, Jingyou Xie, Yinghui Li, Ying Shen

M2-TabFact: Multi-Document Multi-Modal Fact Verification with Visual and Textual Representations of Tabular Data (2025.findings-acl)

Challenge:	Unsupervised Domain Adaptation (UDA) of the Aspect-based Sentiment Analysis task is a data mining technique that involves aspect extraction and aspect sentiment classification subtasks.
Approach:	They propose a framework that allows model parameter transfer, not data transfer, between different domains.
Outcome:	The proposed framework performs competitively with traditional unsupervised domain adaptation methods under privacy conditions.

Copied to clipboard

Mingyang Zhou, Lingyu Zhang, Sophia Horng, Maximillian Chen, Kung-Hsiang Huang, Shih-Fu Chang

From Complexity to Clarity: AI/NLP’s Role in Regulatory Compliance (2025.findings-acl)

Challenge:	Existing fact-checking systems that can reason over structured data are inefficient compared to humans.
Approach:	They propose a multi-modal table-based fact verification task that requires reasoning over visual and textual representations of structured data.
Outcome:	The proposed model can reason over visual and textual representations of structured data.

Copied to clipboard

Jivitesh Jain, Nivedhitha Dhanasekaran, Mona T. Diab

Challenge:	Recent advances in natural language processing have demonstrated remarkable capabilities in text analysis and reasoning.
Approach:	They propose to use standardized evaluation frameworks and balanced human-AI collaboration to address these challenges.
Outcome:	The proposed research will focus on standardized evaluation frameworks and balanced human-AI collaboration to address these challenges.

text2story: A Python Toolkit to Extract and Visualize Story Components of Narrative Text (2024.lrec-main)

Copied to clipboard

Evelin Amorim, Ricardo Campos, Alipio Jorge, Pedro Mota, Rúben Almeida

Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph (2026.acl-long)

Challenge:	Story components, namely events, time, participants, and their relations, are present in narrative texts from different domains such as journalism, medicine, finance, and law.
Approach:	They propose to use an array of narrative extraction tools to extract narratives from text . the package contains an array and an experimental module for evaluation .
Outcome:	The text2story python supports the narrative extraction and visualization pipeline.

Copied to clipboard

Lirong Gao, Zewei Yu, Zhongrui Yin, Qi Zhang, Yuke Zhu, Bo Zheng, Haobo Wang, Junbo Zhao, Gang Chen, Sheng Guo

Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement (2025.acl-long)

Challenge:	Tabular data is used in fields such as finance and healthcare due to its heterogeneity and complexity.
Approach:	They propose a Logic-Graph-Enhanced LLM Reasoning framework that integrates the strengths of tree-based models and LLMs to improve their interpretability.
Outcome:	The proposed framework outperforms tree-based models and state-of-the-art LLMs on tabular prediction tasks, achieving superior accuracy and interpretability.

Copied to clipboard

Yaxuan Kong, Yiyuan Yang, Yoontae Hwang, Wenjie Du, Stefan Zohren, Zhangyang Wang, Ming Jin, Qingsong Wen

Prompting the Unknown: Understanding Response Uncertainty in Large Language Models (2026.findings-acl)

Challenge:	Existing time series models focus on a narrow spectrum of tasks, such as forecasting or anomaly detection.
Approach:	They propose a framework that enables natural language queries across multiple time series tasks such as numerical analytical tasks and open-ended question answering with reasoning.
Outcome:	The proposed framework enables natural language queries across multiple time series tasks and allows for more advanced and intuitive interactions with temporal data.

Copied to clipboard

Ze Yu Zhang, Arun Verma, Finale Doshi-Velez, Bryan Kian Hsiang Low

Demystifying Domain-adaptive Post-training for Financial LLMs (2025.emnlp-main)

Challenge:	Large language models are widely used in decision-making across diverse domains.
Approach:	They propose a prompt-response concept model that explains the relationship between the amount of task-relevant information provided in the prompt and the LLM-generated response uncertainty by identifying four sources of response uncertainty.
Outcome:	The proposed model shows that the amount of information provided in the prompt influences the LLM-generated response uncertainty.

Copied to clipboard

Zixuan Ke, Yifei Ming, Xuan-Phi Nguyen, Caiming Xiong, Shafiq Joty

Confidence Should Be Calibrated More Than One Turn Deep (2026.acl-long)

Challenge:	Domain-adaptive post-training of large language models (LLMs) has emerged as promising approach for specialized domains such as medicine and finance.
Approach:	They propose a system to identify optimal adaptation criteria and training strategies for LLMs for the finance domain.
Outcome:	The proposed model achieves state-of-the-art performance across a wide range of financial tasks.

Copied to clipboard

Zhaohan Zhang, Chengzhengxu Li, Xiaoming Liu, Chao Shen, Ziquan Liu, Ioannis Patras

Machine Translation

Challenge:	Existing work on confidence estimation and calibration focuses on single-turn settings . existing work on multi-turn calibration ignores the risks and potential of multi-turned conversations .
Approach:	They propose a multi-turn calibration task that reframes calibration from a static property into a dynamic challenge central to reliable multi- turn conversations.
Outcome:	The proposed model minimizes ECE@T and leverages ConfChat to improve confidence . the proposed model preserves and even enhances model performance in multi-turn interactions.

Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain (2026.acl-long)

Copied to clipboard

Gang Cheng, Haibo Jin, Wenbin Zhang, Haohan Wang, Jun Zhuang

From Tasks to Teams: A Risk-First Evaluation Framework for Multi-Agent LLM Systems in Finance (2026.findings-acl)

Challenge:	Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as finance where unsafe behavior can lead to serious regulatory risks.
Approach:	They propose a black-box multi-turn risk-concealed redteaming framework that progressively conceals surface-level risk while exploiting regulatory-violating behaviors.
Outcome:	Experiments on nine widely used LLMs show that the proposed framework achieves 93.19% average attack success rate (ASR) and improves the average ASR to 95.00%.

Copied to clipboard

Zichen Chen, Jianda Chen, Jiaao Chen, Misha Sra

Challenge:	Existing benchmarks focus on task specific metrics such as accuracy, F1 score, or ROUGE.
Approach:	They propose a multi-agent, safety-aware evaluation agent that audits large language models without fine-tuning.
Outcome:	M-SAEA identifies unsafe trajectories with minimal false positives and reveals latent risks that are not addressed by standard metrics.

MaskTab: Scalable Masked Tabular Pretraining with Scaling Laws and Distillation for Industrial Classification (2026.findings-acl)

Copied to clipboard

Bo Zheng, Yudong Chen, Zihua Xiong, Shuai Fang, Peidong He, Yang Yang, Sheng Guo