AIConfPaper
← Search

Xinliang Frederick Zhang

13 accepted papers

2026

LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?

Kaijian Zou, Feiyang Xiong, Yunxiang Zhang, Xinliang Frederick Zhang, Yueqi Ren, Shitanshu Bhushan +3
ICML 2026poster

Competitive programming problems are increasingly used to evaluate the coding capabilities of large language models (LLMs) due to their complexity and ease of verification. Yet, current coding benchmarks face limitations such as lack of exceptionally challenging problems, insufficient test case cove…

Cited by 0Source ↗code ↗Scholar ↗
2025

PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process

Xinliang Frederick Zhang, Nicholas Beauchamp, Lu Wang
EMNLP 2025

Large language model (LLM) personalization aims to align model outputs with individuals’ unique preferences and opinions. While recent efforts have implemented various personalization methods, a unified theoretical framework that can systematically understand the drivers of effective personalization

Cited by 12Source ↗PDF ↗Scholar ↗
2024

MOKA: Moral Knowledge Augmentation for Moral Event Extraction

Xinliang Frederick Zhang, Winston Wu, Nicholas Beauchamp, Lu Wang
NAACL 2024long

News media often strive to minimize explicit moral language in news articles, yet most articles are dense with moral values as expressed through the reported events themselves. However, values that are reflected in the intricate dynamics among *participating entities* and *moral events* are far more…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2024

Narrative-of-Thought: Improving Temporal Reasoning of Large Language Models via Recounted Narratives

Xinliang Frederick Zhang, Nicholas Beauchamp, Lu Wang
EMNLP 2024finding

Reasoning about time and temporal relations is an integral aspect of human cognition, essential for perceiving the world and navigating our experiences. Though large language models (LLMs) have demonstrated impressive performance in many reasoning tasks, temporal reasoning remains challenging due to…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

ULTRA: Unleash LLMs’ Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinement

Xinliang Frederick Zhang, Carter Blum, Temma Choji, Shalin Shah, Alakananda Vempala
ACL 2024findings

Structural extraction of events within discourse is critical since it avails a deeper understanding of communication patterns and behavior trends. Event argument extraction (EAE), at the core of event-centric understanding, is the task of identifying role-specific text spans (i.e., arguments) for a…

Cited by 13Source ↗PDF ↗Scholar ↗
2023

All Things Considered: Detecting Partisan Events from News Media with Cross-Article Comparison

Yujian Liu, Xinliang Frederick Zhang, Kaijian Zou, Ruihong Huang, Nicholas Beauchamp, Lu Wang
EMNLP 2023long main

Public opinion is shaped by the information news media provide, and that information in turn may be shaped by the ideological preferences of media outlets. But while much attention has been devoted to media bias via overt ideological language or topic selection, a more unobtrusive way in which the m…

Cited by 0Source ↗code ↗Scholar ↗
2023

Crossing the Aisle: Unveiling Partisan and Counter-Partisan Events in News Reporting

Kaijian Zou, Xinliang Frederick Zhang, Winston Wu, Nicholas Beauchamp, Lu Wang
EMNLP 2023short findings

News media is expected to uphold unbiased reporting. Yet they may still affect public opinion by selectively including or omitting events that support or contradict their ideological positions. Prior work in NLP has only studied media bias via linguistic style and word usage. In this paper, we s…

Cited by 0Source ↗code ↗Scholar ↗
2023

You Are What You Annotate: Towards Better Models through Annotator Representations

Naihao Deng, Xinliang Frederick Zhang, Siyang Liu, Winston Wu, Lu Wang, Rada Mihalcea
EMNLP 2023long findings

Annotator disagreement is ubiquitous in natural language processing (NLP) tasks. There are multiple reasons for such disagreements, including the subjectivity of the task, difficult cases, unclear guidelines, and so on. Rather than simply aggregating labels to obtain data annotations, we instead try…

Cited by 0Source ↗code ↗Scholar ↗
2022

Generative Entity-to-Entity Stance Detection with Knowledge Graph Augmentation

Xinliang Frederick Zhang, Nick Beauchamp, Lu Wang
EMNLP 2022main

Stance detection is typically framed as predicting the sentiment in a given text towards a target entity. However, this setup overlooks the importance of the source entity, i.e., who is expressing the opinion. In this paper, we emphasize the imperative need for studying interactions among entities w…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2022

Late Fusion with Triplet Margin Objective for Multimodal Ideology Prediction and Analysis

Changyuan Qiu, Winston Wu, Xinliang Frederick Zhang, Lu Wang
EMNLP 2022main

Prior work on ideology prediction has largely focused on single modalities, i.e., text or images. In this work, we introduce the task of multimodal ideology prediction, where a model predicts binary or five-point scale ideological leanings, given a text-image pair with political content. We first co…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2022

POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection

Yujian Liu, Xinliang Frederick Zhang, David Wegsman, Nicholas Beauchamp, Lu Wang
NAACL 2022findings

Ideology is at the core of political science research. Yet, there still does not exist general-purpose tools to characterize and predict ideology across different genres of text. To this end, we study Pretrained Language Models using novel ideology-driven pretraining objectives that rely on the comp…

Cited by 83Source ↗PDF ↗code ↗Scholar ↗
2021

COUGH: A Challenge Dataset and Models for COVID-19 FAQ Retrieval

Xinliang Frederick Zhang, Heming Sun, Xiang Yue, Simon Lin, Huan Sun
EMNLP 2021main

We present a large, challenging dataset, COUGH, for COVID-19 FAQ retrieval. Similar to a standard FAQ dataset, COUGH consists of three parts: FAQ Bank, Query Bank and Relevance Set. The FAQ Bank contains ~16K FAQ items scraped from 55 credible websites (e.g., CDC and WHO). For evaluation, we introdu…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2021

Identifying inherent disagreement in natural language inference

Xinliang Frederick Zhang, Marie-Catherine de Marneffe
NAACL 2021long

Natural language inference (NLI) is the task of determining whether a piece of text is entailed, contradicted by or unrelated to another piece of text. In this paper, we investigate how to tease systematic inferences (i.e., items for which people agree on the NLI label) apart from disagreement items…

Cited by 24Source ↗PDF ↗Scholar ↗