Papers by Zhuohan Xie

16 papers
RealFin: How Well Do LLMs Reason About Finance When Users Leave Things Unsaid? (2026.findings-acl)

Copied to clipboard

Challenge: General-purpose models tend to over-commit and guess, while most finance-specialized models fail to clearly identify missing premises.
Approach: They propose a bilingual benchmark that removes premises from exam-style questions while keeping them linguistically plausible.
Outcome: The proposed model overcommits and guesses while most finance-specialized models fail to clearly identify missing premises.
FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning (2026.acl-long)

Copied to clipboard

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

Copied to clipboard

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.
Entity Framing and Role Portrayal in the News (2025.findings-acl)

Copied to clipboard

Challenge: a dataset of news articles containing 22 fine-grained characters is annotated for entity framing and role portrayal . the dataset includes 1,378 recent news articles in five languages focusing on the Ukraine-Russia War and climate change .
Approach: They propose a multilingual and hierarchical corpus annotated for entity framing and role portrayal in news articles.
Outcome: The proposed dataset includes 1,378 recent news articles in five languages focusing on the Ukraine-Russia War and climate change . the authors report evaluation results on state-of-the-art multilingual transformers and hierarchical zero-shot learning using LLMs at the level of a document, paragraph, and sentence .
DeltaScore: Fine-Grained Story Evaluation with Perturbations (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluation metrics for stories are limited in assessing intricate aspects of storytelling, such as fluency and interestingness.
Approach: They propose a novel method that uses perturbation techniques to evaluate story aspects . they compare fluency, coherence, relatedness, logicality, interestingness and interestingness to existing metrics .
Outcome: The proposed method shows that one specific perturbation is highly effective in capturing multiple aspects.
KazMMLU: Evaluating Language Models on Kazakh, Russian, and Regional Knowledge of Kazakhstan (2025.acl-long)

Copied to clipboard

Challenge: Kazakh language remains underrepresented in the field of natural language processing despite the country's population exceeding twenty million . however, there is a lack of dedicated models and benchmark evaluations specifically tailored to Kazakh languages.
Approach: They propose to create a dataset specifically designed for Kazakh language with 23,000 questions sourced from authentic educational materials and manually validated by native speakers and educators.
Outcome: The first MMLU-style dataset specifically designed for Kazakh language.
A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs (2025.emnlp-main)

Copied to clipboard

Challenge: Uncertainty quantification (UQ) is a framework for assessing the reliability of model outputs.
Approach: They introduce pre-trained UQ heads for LLMs that are highly robust and generalized to languages they were not explicitly trained on.
Outcome: The pre-trained heads significantly improve their ability to capture uncertainty compared to unsupervised methods.
FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering (2026.findings-acl)

Copied to clipboard

Challenge: Existing reranking frameworks optimize semantic relevance, leading to unstable rankings and opaque decisions on long documents.
Approach: They propose a structured reranking framework that reframes financial evidence selection as constraint satisfaction under a finance-aware schema.
Outcome: FINCARDS improves early-rank retrieval over lexical and LLM-based reranking baselines while reducing ranking variance.
Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AI (2026.acl-long)

Copied to clipboard

Challenge: Prior studies have shown that distinguishing text generated by Large Language Models from human-written text is challenging for humans and often no better than random guessing.
Approach: They conduct extensive case study to determine the upper bound of human detection accuracy.
Outcome: The findings challenge previous conclusions on human detection accuracy across languages and domains.
LLM-DetectAIve: a Tool for Fine-Grained Machine-Generated Text Detection (2024.emnlp-demo)

Copied to clipboard

Challenge: a large number of machine-generated texts are often hard to distinguish between human-written and machine-generated text . this raises concerns about potential misuse, especially within educational and academic domains .
Approach: They propose a system that can detect whether a text is human-written or machine-generated . they use a fine-grained classification schema to identify the use of machine-generated text .
Outcome: The proposed system can distinguish between human-written and machine-generated text . it can detect attempts to obfuscate the fact that a text was machine- generated .
SAHM: A Benchmark for Arabic Financial and Shari’ah-Compliant Reasoning (2026.acl-long)

Copied to clipboard

Challenge: English financial NLP has progressed rapidly through benchmarks for sentiment, document understanding, and financial question answering.
Approach: They propose a document-grounded benchmark and instruction-tuning dataset for Arabic financial NLP and Shari’ah-compliant reasoning.
Outcome: The proposed dataset contains 14,380 expert-verified instances spanning seven tasks . it includes financial sentiment analysis, extractive summarization, and event–cause reasoning .
FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosure (2026.acl-demo)

Copied to clipboard

Challenge: FinReporting is an agentic workflow for localized cross-jurisdiction financial reporting . existing approaches assume a single-market setting and overlook structural differences across jurisdictions .
Approach: They propose a workflow that decomposes financial reporting into auditable stages . they use Large Language Models to extract and summarize corporate disclosures .
Outcome: The proposed system decomposes reporting into auditable stages . it improves consistency and reliability under heterogeneous reporting regimes.
FIRE: Fact-checking with Iterative Retrieval and Verification (2025.findings-naacl)

Copied to clipboard

Challenge: Fact-checking long-form text is challenging, and breaking it down into multiple atomic claims is not cost-effective.
Approach: They propose a novel agent-based framework that integrates evidence retrieval and claim verification in an iterative manner.
Outcome: The proposed framework reduces large language model (LLM) costs by an average of 7.6 times and search costs by 16.5 times while retaining the same performance.
Can LLMs Automate Fact-Checking Article Writing? (2026.tacl-1)

Copied to clipboard

Challenge: Existing tools for automatic fact-checking produce little or no justification for their assessments . 80% of american adults on major social media platforms regularly encounter news-related content .
Approach: They propose to extend automatic fact-checking pipeline with automatic generation of full fact- checking articles.
Outcome: The proposed framework outperforms existing frameworks but lags behind expert-written articles.
VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration (2025.findings-acl)

Copied to clipboard

Challenge: Existing safety calibration methods focus on model undersafety, where the model responds to hazardous queries, while neglecting oversafetiness, where models refuse to answer safe queries.
Approach: They propose safety calibration which addresses both undersafety and oversafetiness by comparing model responses to a novel dataset of 3,600 image-text pairs.
Outcome: The proposed methods have been used to evaluate safety calibration across image-centric and text-centric scenarios.
Cultural Benchmarking of LLMs in Standard and Dialectal Arabic Dialogues (2026.acl-long)

Copied to clipboard

Challenge: Most benchmarks focus on short text snippets in Modern Standard Arabic (MSA), overlooking cultural nuances that naturally arise in dialogues.
Approach: They propose a culturally grounded conversational dataset covering 13 Arabic-speaking countries, in both Modern Standard Arabic (MSA) and each country’s respective dialect, spanning 12 daily-life topics and 54 fine-grained subtopics.
Outcome: The proposed model performs worse on all three tasks than the MSA benchmark.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations