Papers by Shuai Lin

10 papers
Omni-Chart-600K: A Comprehensive Dataset of Chart Types for Chart Understanding (2025.findings-naacl)

Copied to clipboard

Challenge: Existing chart-related training methods lack capabilities in information extraction, mathematical reasoning, and understanding of multiple chart types.
Approach: They propose a two-stage training strategy and method for jointly training a vision encoder tailored for multi-type charts to address the deficiencies in chart types and limited scope of chart tasks in existing datasets.
Outcome: The proposed dataset includes 21 diverse chart types and tasks, including data retrieval and mathematical reasoning.
Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing models struggle to balance predictive accuracy with human-understandable rationales.
Approach: They propose to enhance LLMs by leveraging rationale distillation and domain knowledge injection for trustworthy multimodal rationale generation.
Outcome: Experiments on real-world medical datasets show that ClinRaGen achieves state-of-the-art performance in disease diagnosis and rationale generation.
Sentiment-Aware Word and Sentence Level Pre-training for Sentiment Analysis (2022.emnlp-main)

Copied to clipboard

Challenge: Existing pre-trained language representation models (PLMs) capture sentiment information from word-level while under-considering sentence-level information.
Approach: They propose a Sentiment-aware pre-trained language model with combined Word-level and Sentence-level Pre-training tasks that enhance the PLM’s knowledge about sentiment words.
Outcome: The proposed model achieves state-of-the-art on various sentence-level and aspect-level sentiment classification benchmarks.
A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation (2026.findings-acl)

Copied to clipboard

Challenge: Existing evaluation methods for mobile GUI agents rely on static frame assessments or offline static apps.
Approach: They propose an evaluation system that leverages large language models as reward models to verify task completion and process achievement.
Outcome: The proposed system addresses the limitations of traditional function based evaluation methods on online dynamic apps.
Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language.
Approach: They propose a model that integrates symbolic data into LLM training without loss of generality ability.
Outcome: The proposed model performs better on symbol- and NL-centric tasks.
Multi-level Relevance Document Identifier Learning for Generative Retrieval (2025.acl-long)

Copied to clipboard

Challenge: Existing methods generate DocIDs based on textual content, which may result in weak semantic connections for similar documents due to variations in expression.
Approach: They propose a new retrieval paradigm that generates unique document identifiers . they propose to use queries as a bridge to connect documents with varying relevance levels .
Outcome: The proposed approach outperforms existing methods on multilingual e-commerce search datasets.
Data-to-Text Generation with Style Imitation (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent approaches to data-to-text generation focus on improving content fidelity, but lack explicit control over writing styles.
Approach: They propose a way to control writing styles by using existing sentences as "soft" templates . they conduct experiments in restaurants and sports domains to test their approach .
Outcome: The proposed approach achieves stronger performance than a range of comparison methods.
ProMedTS: A Self-Supervised, Prompt-Guided Multimodal Approach for Integrating Medical Text and Time Series (2025.findings-acl)

Copied to clipboard

Challenge: Large language models excel at processing unstructured data, but integrating time series data with text remains a challenge.
Approach: They propose a self-supervised multimodal framework that uses prompt-guided learning to unify heterogeneous data types.
Outcome: The proposed framework outperforms state-of-the-art approaches on disease diagnosis tasks using real-world datasets.
Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) are used to review academic papers, but are susceptible to textual adversarial attacks.
Approach: They evaluate the robustness of large language models as automated reviewers in the presence of adversarial attacks.
Outcome: The proposed model is robust against textual adversarial attacks, the authors argue . their findings highlight the importance of addressing adversarials to ensure integrity of scholarly communication.
Competition-Level Problems are Effective LLM Evaluators (2024.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated impressive reasoning capabilities, yet there is ongoing debate about their capabilities and the potential data contamination problem.
Approach: They propose to evaluate the reasoning capabilities of large language models in solving recent competition-level programming problems in Codeforces.
Outcome: The proposed model has experienced a cliff-like decline in problems after September 2021, which shows the potential data contamination and the challenges for any existing LLM to solve unseen complex reasoning problems.

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