Papers by Xinyi Zhao

15 papers
Towards Comprehensive Argument Analysis in Education: Dataset, Tasks, and Method (2025.acl-long)

Copied to clipboard

Challenge: Existing research on argument mining has proposed various argument annotation schemes and tasks.
Approach: They propose a framework comprising 14 fine-grained relation types to capture the interplay between argument components for a thorough understanding of argument structure.
Outcome: The proposed framework captures the interplay between argument components for a thorough understanding of argument structure.
CEAMC: Corpus and Empirical Study of Argument Analysis in Education via LLMs (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing argument component classifications in education are simplistic and isolated, failing to capture the complete argument information.
Approach: They propose to annotate a manually annotated argument component classification dataset from authentic examination settings and to explore the performance of Large Language Models on CEAMC.
Outcome: The proposed dataset can be used to analyze argumentative essays in education.
Uncovering Scaling Laws for Large Language Models via Inverse Problems (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have achieved remarkable success across diverse domains.
Approach: inverse problems can efficiently uncover scaling laws that guide the building of LLMs, authors argue . authors propose brute-force approaches to improve LLM training costs due to high costs .
Outcome: This paper advocates that inverse problems can efficiently uncover scaling laws that guide the building of LLMs to achieve the desirable performance with significantly better cost-effectiveness.
PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy (2025.acl-long)

Copied to clipboard

Challenge: Existing pipelines that combine document image restoration with semantic-aware post-OCR correction can improve text extraction from degraded images.
Approach: They propose a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual consistency.
Outcome: The proposed pipeline reduces character error rates by 63.9-70.3% on 13,831 pages of real historical documents in English, French, and Spanish compared to OCR on raw images.
LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations (2025.coling-main)

Copied to clipboard

Challenge: Lack of training data leads to the system cold-start problem in recommendation systems, making them struggle to provide effective recommendations.
Approach: They propose a tree-based LLM recommendation framework which structures all items into an item tree to improve the efficiency of LLM’s item retrieval.
Outcome: The proposed framework outperforms the baseline model in the A/B test on Huawei industrial system.
P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Defending Large Language Models (LLMs) against backdoors has long been trapped in a "cat-and-mouse" dilemma where defenders passively react to ever-shifting attack strategies.
Approach: They propose a general and effective defense algorithm that implants benign triggers to reshape the model’s decision boundary.
Outcome: The proposed defense algorithm can neutralize malicious backdoors while preserving task performance.
LLMSurgeon: Diagnosing Data Mixture of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: a lack of transparency in large language models makes auditing their "digital DNA" difficult.
Approach: They propose a framework that casts DMS as an inverse problem under label-shift assumption . they propose LLMScan, a recipe-verifiable evaluation suite built from open-source LLMs .
Outcome: The proposed framework casts DMS as an inverse problem under label-shift assumption . compared with existing frameworks, it recovers domain mixtures with high fidelity .
PersLEARN: Research Training through the Lens of Perspective Cultivation (2023.acl-demo)

Copied to clipboard

Challenge: PersLEARN is a tool designed to facilitate the cultivation of scientific perspectives . junior researchers struggle to identify the perspectives reflected in the literature and struggle to develop their own viewpoints.
Approach: They propose a tool to facilitate the cultivation of scientific perspectives by interacting with a prompt-based model and allowing students to develop their own perspectives explicitly.
Outcome: The proposed tool outperforms baseline approaches across multiple domains of literature from different perspectives.
Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Recent models such as OpenAI o1 and DeepSeek-R1 produce explicit reasoning traces, often via Chain-of-Thought prompting.
Approach: They propose a taxonomy that offers a unified perspective for summarizing existing approaches and categorizing reasoning-based backdoor attacks into associative, passive, and active.
Outcome: The proposed taxonomy categorizes reasoning-based backdoor attacks into associative, passive, and active.
Uni-Retrieval: A Multi-Style Retrieval Framework for STEM’s Education (2025.acl-long)

Copied to clipboard

Challenge: Current retrieval models focus on natural text-image retrieval, which is insufficient for STEM education contexts due to ambiguities in the retrieval process.
Approach: They propose a diverse expression retrieval task tailored to educational scenarios . they extract query style features as prototypes and build a continuously updated Prompt Bank .
Outcome: The proposed model outperforms existing retrieval models in most retrieval tasks.
MEDs for PETs: Multilingual Euphemism Disambiguation for Potentially Euphemistic Terms (2024.findings-eacl)

Copied to clipboard

Challenge: Euphemisms are a linguistic device used to soften or neutralize language that may otherwise be harsh or awkward to state directly.
Approach: They train a multilingual transformer model to disambiguate potentially euphemistic terms in multilingual and cross-lingual settings.
Outcome: The proposed model performs better than monolingual models on the disambiguation task compared to monolingual ones in multilingual and cross-lingual settings.
Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial Training (2022.findings-acl)

Copied to clipboard

Challenge: Existing studies treat named entity recognition as a sequential labeling problem.
Approach: They propose a span selection framework for nested named entity recognition . they propose nesting entities with different input categories would be separately extracted .
Outcome: The proposed framework outperforms competing models on four benchmark datasets.
Exploring Fine-Grained Human Motion Video Captioning (2025.coling-main)

Copied to clipboard

Challenge: Existing video captioning models fail to capture nuanced semantics of videos . existing models generate coarse descriptions of human motions, resulting in poor quality .
Approach: They construct a fine-grained human motion video captioning dataset named BoFiT and a model that generates fine-grain descriptions of human motions via prompting.
Outcome: The proposed model outperforms existing models on comprehensive metrics.
LRBench and Judge-R1: Principled Evaluation and Training of LLM-Based Judges for Long-Context Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for evaluating large language models (LLMs) under long contexts are underexplored.
Approach: They propose a large-scale benchmark for evaluating large language models (LLMs) that combines reinforcement learning with multi-turn search to enable grounded and principle-aware evaluation.
Outcome: The proposed model outperforms single-turn baselines across domains and principles.
Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are powerful automatic evaluators for natural language generation (NLG) tasks, but their uncertainty may limit their deployment in many applications.
Approach: They propose a conformal prediction framework that provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average.
Outcome: The proposed framework provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average.

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