papers

Publications (105)

cs.CL2024

Unveiling Performance Challenges of Large Language Models in Low-Resource Healthcare: A Demographic Fairness Perspective

Yue Zhou, Barbara Di Eugenio, Lu Cheng

This paper studies the performance of large language models (LLMs), particularly regarding demographic fairness, in solving real-world healthcare tasks. We evaluate state-of-the-ar…

cs.SI2021

Mechanisms and Attributes of Echo Chambers in Social Media

Bohan Jiang, Mansooreh Karami, Lu Cheng +2

Echo chambers may exclude social media users from being exposed to other opinions, therefore, can cause rampant negative effects. Among abundant evidence are the 2016 and 2020 US p…

cs.CL2025

Credence Calibration Game? Calibrating Large Language Models through Structured Play

Ke Fang, Tianyi Zhao, Lu Cheng

As Large Language Models (LLMs) are increasingly deployed in decision-critical domains, it becomes essential to ensure that their confidence estimates faithfully correspond to thei…

cs.LG2025

Long-Term Fairness Inquiries and Pursuits in Machine Learning: A Survey of Notions, Methods, and Challenges

Usman Gohar, Zeyu Tang, Jialu Wang +4

The widespread integration of Machine Learning systems in daily life, particularly in high-stakes domains, has raised concerns about the fairness implications. While prior works ha…

cs.SI2022

Bridging the Gap: Commonality and Differences between Online and Offline COVID-19 Data

Nayoung Kim, Ahmadreza Mosallanezhad, Lu Cheng +2

With the onset of the COVID-19 pandemic, news outlets and social media have become central tools for disseminating and consuming information. Because of their ease of access, users…

cs.LG2026

TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning

Fangxu Yu, Tao Feng, Dehai Min +3

Time series reasoning is essential for real-world problem-solving. While both Large Language Models (LLMs) and Vision-Language Models (VLMs) can reason about time-series data, thei…

cs.CL2025

Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology

Longchao Da, Xiaoou Liu, Jiaxin Dai +3

Understanding the uncertainty in large language model (LLM) explanations is important for evaluating their faithfulness and reasoning consistency, and thus provides insights into t…

cs.CL2024

LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation

Longchao Da, Tiejin Chen, Lu Cheng +1

The Large language models (LLMs) have showcased superior capabilities in sophisticated tasks across various domains, stemming from basic question-answer (QA), they are nowadays use…

cs.CL2026

Early Risk Prediction with Temporally and Contextually Grounded Clinical Language Processing

Rochana Chaturvedi, Yue Zhou, Andrew D. Boyd +5

Clinical notes in Electronic Health Records (EHRs) capture rich temporal information on events, clinician reasoning, and lifestyle factors often missing from structured data. Lever…

cs.CY2021

Automated Meta-Analysis: A Causal Learning Perspective

Lu Cheng, Dmitriy A. Katz-Rogozhnikov, Kush R. Varshney +1

Meta-analysis is a systematic approach for understanding a phenomenon by analyzing the results of many previously published experimental studies. It is central to deriving conclusi…

cs.CL2026

Self-correction is Not An Innate Capability in Language Models

Guangliang Liu, Zimo Qi, Xitong Zhang +2

Although there has been growing interest in the self-correction capability of Large Language Models (LLMs), there are varying conclusions about its effectiveness. Prior research ha…

cs.CL2024

Assessing Empathy in Large Language Models with Real-World Physician-Patient Interactions

Man Luo, Christopher J. Warren, Lu Cheng +2

The integration of Large Language Models (LLMs) into the healthcare domain has the potential to significantly enhance patient care and support through the development of empathetic…

cs.CL2024

API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access

Jiayuan Su, Jing Luo, Hongwei Wang +1

This study aims to address the pervasive challenge of quantifying uncertainty in large language models (LLMs) without logit-access. Conformal Prediction (CP), known for its model-a…

cs.CL2025

Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models

Liangjie Huang, Dawei Li, Huan Liu +1

Large Language Models (LLMs) have demonstrated remarkable self-improvement capabilities, whereby models iteratively revise their outputs through self-generated feedback. While this…

cs.CL2022

Toward Understanding Bias Correlations for Mitigation in NLP

Lu Cheng, Suyu Ge, Huan Liu

Natural Language Processing (NLP) models have been found discriminative against groups of different social identities such as gender and race. With the negative consequences of the…

math.NA2023

Solving time-dependent PDEs with the ultraspherical spectral method

Lu Cheng, Kuan Xu

We apply the ultraspherical spectral method to solving time-dependent PDEs by proposing two approaches to discretization based on the method of lines and show that these approaches…

cs.CL2026

QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation

Dehai Min, Kailin Zhang, Tongtong Wu +1

Dynamic Retrieval-Augmented Generation adaptively determines when to retrieve during generation to mitigate hallucinations in large language models (LLMs). However, existing method…

cs.AI2025

From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge

Dawei Li, Bohan Jiang, Liangjie Huang +10

Assessment and evaluation have long been critical challenges in artificial intelligence (AI) and natural language processing (NLP). Traditional methods, usually matching-based or s…

cs.SI2020

Unsupervised Cyberbullying Detection via Time-Informed Gaussian Mixture Model

Lu Cheng, Kai Shu, Siqi Wu +3

Social media is a vital means for information-sharing due to its easy access, low cost, and fast dissemination characteristics. However, increases in social media usage have corres…

cs.LG2024

Overcoming Pitfalls in Graph Contrastive Learning Evaluation: Toward Comprehensive Benchmarks

Qian Ma, Hongliang Chi, Hengrui Zhang +6

The rise of self-supervised learning, which operates without the need for labeled data, has garnered significant interest within the graph learning community. This enthusiasm has l…

cs.CL2025

SoM-1K: A Thousand-Problem Benchmark Dataset for Strength of Materials

Qixin Wan, Zilong Wang, Jingwen Zhou +6

Foundation models have shown remarkable capabilities in various domains, but their performance on complex, multimodal engineering problems remains largely unexplored. We introduce…

cs.LG2022

Effects of Multi-Aspect Online Reviews with Unobserved Confounders: Estimation and Implication

Lu Cheng, Ruocheng Guo, Kasim Selcuk Candan +1

Online review systems are the primary means through which many businesses seek to build the brand and spread their messages. Prior research studying the effects of online reviews h…

cs.LG2026

The Confidence Trap: Calibration Attacks for Graph Neural Networks

Cuong Dang, Jiahao Zhang, Hieu Ta Quang +3

While confidence calibration is essential for trustworthy decision-making in safety-critical applications, the robustness of calibrated GNNs to adversarial structural perturbations…

cs.LG2026

MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series

Shicheng Fan, Nour Elhendawy, Jianle Sun +4

Causal representation learning (CRL) seeks to recover latent variables with identifiability guarantees, typically up to permutation and component-wise reparameterization under appr…

cs.LG2023

A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges

Usman Gohar, Lu Cheng

The widespread adoption of Machine Learning systems, especially in more decision-critical applications such as criminal sentencing and bank loans, has led to increased concerns abo…

cs.CR2026

POISE: Position-Aware Undetectable Skill Injection on LLM Agents

Haochang Hao, Dehai Min, Zhifang Zhang +4

Agent skills provide a lightweight mechanism for extending general-purpose agents, but their open format exposes them to skill-poisoning attacks. A practically dangerous injection…

cs.LG2025

Robust Uncertainty Quantification for Self-Evolving Large Language Models via Continual Domain Pretraining

Xiaofan Zhou, Lu Cheng

Continual Learning (CL) is essential for enabling self-evolving large language models (LLMs) to adapt and remain effective amid rapid knowledge growth. Yet, despite its importance,…

cs.CL2025

A Large Language Model-Empowered Agent for Reliable and Robust Structural Analysis

Jiachen Liu, Ziheng Geng, Ran Cao +3

Large language models (LLMs) have exhibited remarkable capabilities across diverse open-domain tasks, yet their application in specialized domains such as civil engineering remains…

cs.CL2026

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Dehai Min, Giovanni Vaccarino, Huiyi Chen +3

Large Reasoning Models (LRMs) achieve strong performance by generating long chains of thought (CoT), but often overthink, continuing to reason after a solution has already stabiliz…

cs.CL2025

DemoShapley: Valuation of Demonstrations for In-Context Learning

Shan Xie, Man Luo, Chadly Daniel Stern +2

Large language models (LLMs) using in-context learning (ICL) excel in many tasks without task-specific fine-tuning. However, demonstration selection and ordering greatly impact ICL…

cs.LG2022

Distributional Shift Adaptation using Domain-Specific Features

Anique Tahir, Lu Cheng, Ruocheng Guo +1

Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming…

cs.CL2026

URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models

Vinh Nguyen, Cuong Dang, Jiahao Zhang +6

Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for enhancing LLMs in scenarios that demand extensive factual knowledge. However, current RAG evaluati…

stat.ML2022

Causal Mediation Analysis with Hidden Confounders

Lu Cheng, Ruocheng Guo, Huan Liu

An important problem in causal inference is to break down the total effect of a treatment on an outcome into different causal pathways and to quantify the causal effect in each pat…

cs.LG2022

Estimating Causal Effects of Multi-Aspect Online Reviews with Multi-Modal Proxies

Lu Cheng, Ruocheng Guo, Huan Liu

Online reviews enable consumers to engage with companies and provide important feedback. Due to the complexity of the high-dimensional text, these reviews are often simplified as a…

cs.CV2026

MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs

Huiyi Chen, Jiawei Peng, Dehai Min +5

Evaluating the robustness of Large Vision-Language Models (LVLMs) is essential for their continued development and responsible deployment in real-world applications. However, exist…

cs.CL2022

Debiasing Word Embeddings with Nonlinear Geometry

Lu Cheng, Nayoung Kim, Huan Liu

Debiasing word embeddings has been largely limited to individual and independent social categories. However, real-world corpora typically present multiple social categories that po…

cs.LG2025

Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs

Jiancheng Dong, Lei Jiang, Wei Jin +1

Packing for Supervised Fine-Tuning (SFT) in autoregressive models involves concatenating data points of varying lengths until reaching the designed maximum length to facilitate GPU…

cs.LG2023

A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier

Hua Tang, Lu Cheng, Ninghao Liu +1

While the accuracy-fairness trade-off has been frequently observed in the literature of fair machine learning, rigorous theoretical analyses have been scarce. To demystify this lon…

cs.LG2023

Fair Few-shot Learning with Auxiliary Sets

Song Wang, Jing Ma, Lu Cheng +1

Recently, there has been a growing interest in developing machine learning (ML) models that can promote fairness, i.e., eliminating biased predictions towards certain populations (…

cs.LG2024

Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML

Prakhar Ganesh, Usman Gohar, Lu Cheng +1

With fairness concerns gaining significant attention in Machine Learning (ML), several bias mitigation techniques have been proposed, often compared against each other to find the…

cs.CL2024

ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees

Zhiyuan Wang, Jinhao Duan, Lu Cheng +6

Uncertainty quantification (UQ) in natural language generation (NLG) tasks remains an open challenge, exacerbated by the closed-source nature of the latest large language models (L…

cs.AI2026

A Novel Multi-Agent Architecture to Reduce Hallucinations of Large Language Models in Multi-Step Structural Modeling

Ziheng Geng, Jiachen Liu, Ran Cao +3

Large language models (LLMs) such as GPT and Gemini have demonstrated remarkable capabilities in contextual understanding and reasoning. The strong performance of LLMs has sparked…

cs.CY2021

Causal Understanding of Fake News Dissemination on Social Media

Lu Cheng, Ruocheng Guo, Kai Shu +1

Recent years have witnessed remarkable progress towards computational fake news detection. To mitigate its negative impact, we argue that it is critical to understand what user att…

cs.CL2026

Context-Aware Counterfactual Data Augmentation for Gender Bias Mitigation in Language Models

Shweta Parihar, Liu Guangliang, Natalie Parde +1

A challenge in mitigating social bias in fine-tuned language models (LMs) is the potential reduction in language modeling capability, which can harm downstream performance. Counter…

cs.CL2025

COPU: Conformal Prediction for Uncertainty Quantification in Natural Language Generation

Sean Wang, Yicheng Jiang, Yuxin Tang +2

Uncertainty Quantification (UQ) for Natural Language Generation (NLG) is crucial for assessing the performance of Large Language Models (LLMs), as it reveals confidence in predicti…

cs.LG2026

SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards

Dengjia Zhang, Xiaoou Liu, Lu Cheng +3

Large language models (LLMs) are increasingly deployed as multi-step decision-making agents, where effective reward design is essential for guiding learning. Although recent work e…

cs.LG2026

Differentiable Conformal Training for LLM Reasoning Factuality

Nathan Hittesdorf, Marco Salzetta, Lu Cheng

Large Language Models (LLMs) frequently hallucinate, limiting their reliability in critical applications. Conformal Prediction (CP) addresses this by calibrating error rates on hel…

cs.CY2023

Intersectionality and Testimonial Injustice in Medical Records

Kenya S. Andrews, Bhuvani Shah, Lu Cheng

Detecting testimonial injustice is an essential element of addressing inequities and promoting inclusive healthcare practices, many of which are life-critical. However, using a sin…

cs.AI2024

Towards Trustworthy Knowledge Graph Reasoning: An Uncertainty Aware Perspective

Bo Ni, Yu Wang, Lu Cheng +2

Recently, Knowledge Graphs (KGs) have been successfully coupled with Large Language Models (LLMs) to mitigate their hallucinations and enhance their reasoning capability, such as i…

cs.CL2023

Interpreting Pretrained Language Models via Concept Bottlenecks

Zhen Tan, Lu Cheng, Song Wang +3

Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. However, the lack of interpretability due to their ``black-box'' natur…

cs.SI2022

Nothing Stands Alone: Relational Fake News Detection with Hypergraph Neural Networks

Ujun Jeong, Kaize Ding, Lu Cheng +3

Nowadays, fake news easily propagates through online social networks and becomes a grand threat to individuals and society. Assessing the authenticity of news is challenging due to…

math.NA2024

Understanding the ultraspherical spectral method

Lu Cheng, Kuan Xu

The ultraspherical spectral method features high accuracy and fast solution. In this article, we determine the sources of error arising from the ultraspherical spectral method and…

cs.AI2025

InsurAgent: A Large Language Model-Empowered Agent for Simulating Individual Behavior in Purchasing Flood Insurance

Ziheng Geng, Jiachen Liu, Ran Cao +3

Flood insurance is an effective strategy for individuals to mitigate disaster-related losses. However, participation rates among at-risk populations in the United States remain str…

cs.LG2024

Conformalized Link Prediction on Graph Neural Networks

Tianyi Zhao, Jian Kang, Lu Cheng

Graph Neural Networks (GNNs) excel in diverse tasks, yet their applications in high-stakes domains are often hampered by unreliable predictions. Although numerous uncertainty quant…

cs.CL2025

CP-Router: An Uncertainty-Aware Router Between LLM and LRM

Jiayuan Su, Fulin Lin, Zhaopeng Feng +7

Recent advances in Large Reasoning Models (LRMs) have significantly improved long-chain reasoning capabilities over Large Language Models (LLMs). However, LRMs often produce unnece…

math.NA2022

On Block Accelerations of Quantile Randomized Kaczmarz for Corrupted Systems of Linear Equations

Lu Cheng, Benjamin Jarman, Deanna Needell +1

With the growth of large data as well as large-scale learning tasks, the need for efficient and robust linear system solvers is greater than ever. The randomized Kaczmarz method (R…

cs.CL2021

Improving Cyberbully Detection with User Interaction

Suyu Ge, Lu Cheng, Huan Liu

Cyberbullying, identified as intended and repeated online bullying behavior, has become increasingly prevalent in the past few decades. Despite the significant progress made thus f…

cs.CL2026

EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering and Reasoning

Mingyang Wei, Dehai Min, Zewen Liu +8

Reliable epidemiological reasoning requires synthesizing study evidence to infer disease burden, transmission dynamics, and intervention effects at the population level. Existing m…

cs.CL2023

Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models

Yueqing Liang, Lu Cheng, Ali Payani +1

This work investigates the potential of undermining both fairness and detection performance in abusive language detection. In a dynamic and complex digital world, it is crucial to…

cs.CL2026

Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens

Weihao Liu, Dehai Min, Lu Cheng

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it constrains the model's thoughts to a discrete vocabulary space. Rec…

cs.AI2020

A Survey of Learning Causality with Data: Problems and Methods

Ruocheng Guo, Lu Cheng, Jundong Li +2

This work considers the question of how convenient access to copious data impacts our ability to learn causal effects and relations. In what ways is learning causality in the era o…

cs.LG2024

Evaluating LLMs Capabilities Towards Understanding Social Dynamics

Anique Tahir, Lu Cheng, Manuel Sandoval +3

Social media discourse involves people from different backgrounds, beliefs, and motives. Thus, often such discourse can devolve into toxic interactions. Generative Models, such as…

cs.CL2024

Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey

Chengyuan Deng, Yiqun Duan, Xin Jin +15

Large Language Models (LLMs) have achieved unparalleled success across diverse language modeling tasks in recent years. However, this progress has also intensified ethical concerns…

q-bio.GN2014

SEK: Sparsity exploiting -mer-based estimation of bacterial community composition

Saikat Chatterjee, David Koslicki, Siyuan Dong +8

Motivation: Estimation of bacterial community composition from a high-throughput sequenced sample is an important task in metagenomics applications. Since the sample sequence data…

cs.CV2022

Human Instance Segmentation and Tracking via Data Association and Single-stage Detector

Lu Cheng, Mingbo Zhao

Human video instance segmentation plays an important role in computer understanding of human activities and is widely used in video processing, video surveillance, and human modeli…

cs.CL2024

LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing

Jiangshu Du, Yibo Wang, Wenting Zhao +37

This work is motivated by two key trends. On one hand, large language models (LLMs) have shown remarkable versatility in various generative tasks such as writing, drawing, and ques…

math.NA2025

A new banded Petrov--Galerkin spectral method

Ouyuan Qin, Lu Cheng, Kuan Xu

We propose a Petrov--Galerkin spectral method for ODEs with variable coefficients. When the variable coefficients are smooth, the new method yields a strictly banded linear system,…

cs.LG2022

Evaluation Methods and Measures for Causal Learning Algorithms

Lu Cheng, Ruocheng Guo, Raha Moraffah +3

The convenient access to copious multi-faceted data has encouraged machine learning researchers to reconsider correlation-based learning and embrace the opportunity of causality-ba…

cs.CL2026

Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution

Xiaoou Liu, Tiejin Chen, Dengjia Zhang +3

Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step reasoning t…

cs.CY2021

Socially Responsible AI Algorithms: Issues, Purposes, and Challenges

Lu Cheng, Kush R. Varshney, Huan Liu

In the current era, people and society have grown increasingly reliant on artificial intelligence (AI) technologies. AI has the potential to drive us towards a future in which all…

cs.LG2025

Conformal Prediction: A Data Perspective

Xiaofan Zhou, Baiting Chen, Yu Gui +1

Conformal prediction (CP), a distribution-free uncertainty quantification (UQ) framework, reliably provides valid predictive inference for black-box models. CP constructs predictio…

stat.AP2020

Long-Term Effect Estimation with Surrogate Representation

Lu Cheng, Ruocheng Guo, Huan Liu

There are many scenarios where short- and long-term causal effects of an intervention are different. For example, low-quality ads may increase short-term ad clicks but decrease the…

cs.LG2026

TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning

Shicheng Fan, Kun Zhang, Lu Cheng

Temporal causal representation learning methods assume that causal mechanisms switch instantaneously between discrete domains, yet real-world systems often exhibit continuous mecha…

cond-mat.mtrl-sci2025

P-orbital spin generator with large spin Hall angle and long spin diffusion length

Gen Li, Ying Zhang, Xiaoguang Xu +10

High density data storage and spin-logic devices require highly efficient all-electric control of spin moments. So far, charge-to-spin conversion through the spin Hall effect (SHE)…

cs.CL2026

Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering

Shicheng Fan, Haochang Hao, Dehai Min +3

Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewards provide only coarse supe…

cs.LG2021

Analysis of Legal Documents via Non-negative Matrix Factorization Methods

Ryan Budahazy, Lu Cheng, Yihuan Huang +7

The California Innocence Project (CIP), a clinical law school program aiming to free wrongfully convicted prisoners, evaluates thousands of mails containing new requests for assist…

cs.LG2023

Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs

Tianyi Zhao, Hui Hu, Lu Cheng

Graph Neural Networks (GNNs) are powerful tools for learning representations on graphs, such as social networks. However, their vulnerability to privacy inference attacks restricts…

cs.LG2024

JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning

Anique Tahir, Lu Cheng, Huan Liu

The scaling of Large Language Models (LLMs) for retrieval-based tasks, particularly in Retrieval Augmented Generation (RAG), faces significant memory constraints, especially when f…

cs.LG2023

Fairness through Aleatoric Uncertainty

Anique Tahir, Lu Cheng, Huan Liu

We propose a simple yet effective solution to tackle the often-competing goals of fairness and utility in classification tasks. While fairness ensures that the model's predictions…

cs.CY2025

Smart Trial: Evaluating the Use of Large Language Models for Recruiting Clinical Trial Participants via Social Media

Xiaofan Zhou, Zisu Wang, Janice Krieger +2

Clinical trials (CT) are essential for advancing medical research and treatment, yet efficiently recruiting eligible participants -- each of whom must meet complex eligibility crit…

cs.SI2022

Improving Vaccine Stance Detection by Combining Online and Offline Data

Anique Tahir, Lu Cheng, Paras Sheth +1

Differing opinions about COVID-19 have led to various online discourses regarding vaccines. Due to the detrimental effects and the scale of the COVID-19 pandemic, detecting vaccine…

cs.CL2025

DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models

Zihao Li, Ruixiang Tang, Lu Cheng +3

Pre-trained language models (PLMs) have achieved impressive results on various natural language processing tasks. However, recent research has revealed that these models often rely…

cs.IR2022

Causal Disentanglement with Network Information for Debiased Recommendations

Paras Sheth, Ruocheng Guo, Lu Cheng +2

Recommender systems aim to recommend new items to users by learning user and item representations. In practice, these representations are highly entangled as they consist of inform…

cs.CL2024

Large Language Models for Data Annotation and Synthesis: A Survey

Zhen Tan, Dawei Li, Song Wang +7

Data annotation and synthesis generally refers to the labeling or generating of raw data with relevant information, which could be used for improving the efficacy of machine learni…

cs.CL2026

Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator

Shiping Yang, Shining Liang, Weihao Liu +4

Identifying faithfulness hallucinations in LLM-generated outputs remains challenging due to the scarcity of high-quality annotated data. Recent work relies on advanced LLMs to synt…

cs.CL2025

Shakespearean Sparks: The Dance of Hallucination and Creativity in LLMs' Decoding Layers

Zicong He, Boxuan Zhang, Lu Cheng

Large language models (LLMs) are known to hallucinate, a phenomenon often linked to creativity. While previous research has primarily explored this connection through theoretical o…

cs.AI2025

What Shapes a Creative Machine Mind? Comprehensively Benchmarking Creativity in Foundation Models

Zicong He, Boxuan Zhang, Weihao Liu +2

The meteoric rise of foundation models (FMs) has expanded their capabilities far beyond conventional tasks. Creativity, long regarded as a hallmark of human intelligence and a driv…

cs.CL2025

Revisiting NLI: Towards Cost-Effective and Human-Aligned Metrics for Evaluating LLMs in Question Answering

Sai Shridhar Balamurali, Lu Cheng

Evaluating answers from state-of-the-art large language models (LLMs) is challenging: lexical metrics miss semantic nuances, whereas "LLM-as-Judge" scoring is computationally expen…

cs.SI2024

Media Bias Matters: Understanding the Impact of Politically Biased News on Vaccine Attitudes in Social Media

Bohan Jiang, Lu Cheng, Zhen Tan +2

News media has been utilized as a political tool to stray from facts, presenting biased claims without evidence. Amid the COVID-19 pandemic, politically biased news (PBN) has signi…

cs.CL2024

Robust Stance Detection: Understanding Public Perceptions in Social Media

Nayoung Kim, David Mosallanezhad, Lu Cheng +2

The abundance of social media data has presented opportunities for accurately determining public and group-specific stances around policy proposals or controversial topics. In cont…

cs.SI2021

A Survey on Echo Chambers on Social Media: Description, Detection and Mitigation

Faisal Alatawi, Lu Cheng, Anique Tahir +4

Echo chambers on social media are a significant problem that can elicit a number of negative consequences, most recently affecting the response to COVID-19. Echo chambers promote c…

cs.CL2026

SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems

Haochang Hao, Yifan Xu, Xinzhuo Li +2

Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction. We identify an underexplored vulnerability in which rec…

cs.CL2024

Direct-Inverse Prompting: Analyzing LLMs' Discriminative Capacity in Self-Improving Generation

Jihyun Janice Ahn, Ryo Kamoi, Lu Cheng +2

Mainstream LLM research has primarily focused on enhancing their generative capabilities. However, even the most advanced LLMs experience uncertainty in their outputs, often produc…

cs.CV2023

Inferring High-level Geographical Concepts via Knowledge Graph and Multi-scale Data Integration: A Case Study of C-shaped Building Pattern Recognition

Zhiwei Wei, Yi Xiao, Wenjia Xu +4

Effective building pattern recognition is critical for understanding urban form, automating map generalization, and visualizing 3D city models. Most existing studies use object-ind…

cs.CL2025

A Lightweight Large Language Model-Based Multi-Agent System for 2D Frame Structural Analysis

Ziheng Geng, Jiachen Liu, Ran Cao +3

Large language models (LLMs) have recently been used to empower autonomous agents in engineering, significantly improving automation and efficiency in labor-intensive workflows. Ho…

cs.IR2025

Accelerating Causal Network Discovery of Alzheimer Disease Biomarkers via Scientific Literature-based Retrieval Augmented Generation

Xiaofan Zhou, Liangjie Huang, Pinyang Cheng +4

The causal relationships between biomarkers are essential for disease diagnosis and medical treatment planning. One notable application is Alzheimer's disease (AD) diagnosis, where…

cs.CL2026

When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification

Jiale Zhao, Ke Fang, Lu Cheng

Large language models (LLMs) often respond even when prompts omit critical details or include misleading information, leading to hallucinations or reinforced misconceptions. We stu…

cs.CL2026

Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts

Shweta Parihar, Lu Cheng

Social biases inherent in large language models (LLMs) raise significant fairness concerns. Retrieval-Augmented Generation (RAG) architectures, which retrieve external knowledge so…

cs.AI2022

Causal Learning for Socially Responsible AI

Lu Cheng, Ahmadreza Mosallanezhad, Paras Sheth +1

There have been increasing concerns about Artificial Intelligence (AI) due to its unfathomable potential power. To make AI address ethical challenges and shun undesirable outcomes,…

cs.CV2025

Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability

Dong Shu, Haiyan Zhao, Jingyu Hu +4

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment betwe…