Papers by Zhen Lin

25 papers
Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are gaining popularity due to their lack of knowledge hallucination and lack of a coherent model.
Approach: They propose a self-supervised quantized representation method to compress KG structural and semantic knowledge into discrete codes that align the format of language sentences.
Outcome: The proposed framework outperforms existing unsupervised methods producing more distinguishable codes on KG link prediction and triple classification tasks.
CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios (2025.emnlp-main)

Copied to clipboard

Challenge: a number of tools are used to perform complex tasks, but the tool utilization process can cause errors.
Approach: They propose a critique evaluation benchmark for tool learning that analyzes function-calling errors on tool evaluation benchmarks.
Outcome: The proposed critique evaluation benchmark holds diverse tool-use errors with varying complexities, which better reflects real-world scenarios.
Rationalizing Medical Relation Prediction from Corpus-level Statistics (2020.acl-main)

Copied to clipboard

Challenge: Existing work on predicting relations based on text corpus has focused on analyzing raw texts mentioning two entities.
Approach: They propose a framework that can be used to rationalize medical relation prediction . they recall contexts associated with the target entities and recognize relational interactions between them .
Outcome: The proposed framework can achieve competitive predictive performance against a comprehensive list of neural baseline models, and present rationales to justify its prediction.
Modalities Should Be Appropriately Leveraged: Uncertainty Guidance for Multimodal Chinese Spelling Correction (2024.lrec-main)

Copied to clipboard

Challenge: Chinese spelling correction (CSC) aims to detect and correct spelling errors in Chinese texts.
Approach: They propose a framework that incorporates uncertainty into feature learning and correction stages . they propose to combine the uncertainty of multimodal features with model learning .
Outcome: The proposed framework improves on three public datasets.
CrowdAgent: Multi-Agent Managed Multi-Source Annotation System (2025.emnlp-demos)

Copied to clipboard

Challenge: Recent approaches to annotate data focus on labeling, but lack holistic process control . a novel system that integrates task assignment, data annotation, and quality/cost management is needed .
Approach: They propose a multi-agent system that integrates task assignment, data annotation, and quality/cost management.
Outcome: The proposed system automates human management by using a collaborative multi-agent system.
A Semi-supervised Scalable Unified Framework for E-commerce Query Classification (2025.acl-industry)

Copied to clipboard

Challenge: Existing query classification methods rely on posterior click behavior to construct training samples, resulting in insufficient prior information for modeling.
Approach: They propose a semi-supervised scaleable unified framework that integrates enhanced modules to unify query classification tasks.
Outcome: The proposed framework outperforms the state-of-the-art models in offline and online A/B experiments.
Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense Framework (2025.emnlp-main)

Copied to clipboard

Challenge: Bit-flip errors (BFEs) are hardware faults where individual bits in memory or processing units are unintentionally flipped.
Approach: They propose a novel defense strategy to mitigate bit-flip errors (BFEs) they propose bfe protection and a self-correction mechanism to minimize performance degradation .
Outcome: The proposed defense strategy minimizes performance degradation while significantly improving robustness against BFEs.
ChartM3: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension (2025.findings-emnlp)

Copied to clipboard

Challenge: Currently, research on complex chart understanding tasks is limited . a pipeline for visual reasoning datasets addresses these limitations .
Approach: They propose a code-driven pipeline for generating visual reasoning datasets . pipeline integrates retrieval-augmented generation to retrieve professional chart templates .
Outcome: The proposed pipeline enhances chart diversity and data quality through model-based evaluation.
UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models (2026.acl-demo)

Copied to clipboard

Challenge: Existing evaluation frameworks for audio foundation models are heavily reliant on English, making it difficult to objectively assess models’ performance on Chinese.
Approach: They propose a unified framework that supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards.
Outcome: The proposed framework supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards.
MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering (2025.findings-acl)

Copied to clipboard

Challenge: Text-Centric Visual Question Answering (TEC-VQA) is a text-centric visual task understanding tool.
Approach: They introduce a benchmark that features human expert annotations across 9 languages . they prioritize the text in question-answer pairs while disregarding visual text in images .
Outcome: The proposed benchmarks prioritize the text in question-answer pairs while disregarding visual text in images.
AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness (2025.acl-long)

Copied to clipboard

Challenge: Existing models that assess mLLMs on harmful meme understanding are inaccurate and lack accuracy.
Approach: They propose a framework that adaptively probes the reasoning capabilities of mLLMs . their framework systematically reveals the varying performance of different target mllms a .
Outcome: The proposed framework systematically reveals the performance of different target mLLMs.
Evaluating Saliency Explanations in NLP by Crowdsourcing (2024.lrec-main)

Copied to clipboard

Challenge: a crowdsourced method to evaluate saliency methods in NLP is proposed . saliencies are difficult for humans to understand, and can cause psychological harm .
Approach: They propose a method to evaluate saliency methods in NLP by crowdsourcing . they recruited 800 crowd workers and empirically evaluated seven salience methods .
Outcome: The proposed method evaluates saliency methods on two datasets using crowdsourced data . it shows that the results are comparable to existing methods on NLP and CV fields .
PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation (2022.findings-aacl)

Copied to clipboard

Challenge: Experimental results show PLATO-XL achieves state-of-the-art results across multiple conversational tasks.
Approach: They propose to train PLATO-XL models with up to 11 billion parameters, trained on Chinese and English social media conversations.
Outcome: The proposed model achieves state-of-the-art on multiple conversational tasks, verifying its potential as a foundation model of conversational AI.
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.
How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior (2026.acl-long)

Copied to clipboard

Challenge: In practice, memory designs vary widely across agents due to their diverse objectives and functionalities.
Approach: They conduct an empirical study on how memory management choices impact the LLM agents’ behavior, especially their long-term performance.
Outcome: The proposed methods show that LLM agents display an experience-following property, which results in highly similar agent outputs.
MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have advanced natural language processing, demonstrating exceptional reasoning, tool usage, and memory capabilities.
Approach: They propose a competition-based benchmark framework specifically designed to assess LLMs within multi-agent environments.
Outcome: The proposed framework enhances the LLMs’ abilities in navigating complex social and cognitive dimensions by over threefold between the strongest and weakest LLM models.
AutoFigure-Edit: Generating Editable Scientific Illustrations via Reference-Guided Styling (2026.acl-demo)

Copied to clipboard

Challenge: Existing automated systems for scientific illustrations are limited in editability, stylistic controllability, and efficiency.
Approach: They propose an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images.
Outcome: The proposed system generates fully editable scientific illustrations from long-form scientific texts while enabling flexible style adaptation through user-provided reference images.
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision (2026.acl-long)

Copied to clipboard

Challenge: Unified Multimodal Models have achieved remarkable success in cross-modal comprehension, but a gap persists in their ability to translate internal knowledge into faithful and controllable synthesis.
Approach: They propose a self-improvement framework that partitions a single UMM into three collaborative roles: Proposer, Solver, and Judge.
Outcome: The proposed framework improves on TIIF, DPG, CompBench and UniCycle benchmarks.
SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities (2025.findings-acl)

Copied to clipboard

Challenge: Emerging large reasoning models (LRMs) leverage long chain-of-thought (CoT) reasoning to enhance their reasoning capabilities.
Approach: They conduct a systematic study of LRM safety using human annotations to assess their safety.
Outcome: The proposed safety measures are compared to state-of-the-art models on strong and wildjailbreak datasets.
PathwiseRAG: Multi-Dimensional Exploration and Integration Framework (2025.emnlp-main)

Copied to clipboard

Challenge: Existing retrieval-augmented generation systems employ rigid retrieval strategies . static retrieval produces knowledge blind spots, missing connections between quantum algorithms and encryption vulnerabilities .
Approach: PathwiseRAG addresses these challenges through intent-aware strategy selection . it constructs a directed acyclic graph of interconnected sub-problems and explores multiple reasoning trajectories .
Outcome: The proposed framework achieves higher accuracy and better reliability than current systems.
ScratchEval: Are GPT-4o Smarter than My Child? Evaluating Large Multimodal Models with Visual Programming Challenges (2025.naacl-short)

Copied to clipboard

Challenge: Recent advances in large multimodal models (LMMs) have demonstrated impressive code generation capabilities, primarily evaluated through image-to-code benchmarks.
Approach: They propose a visual programming reasoning benchmark based on Scratch, a block-based visual programming language widely used in children’s programming education.
Outcome: The proposed framework evaluates the visual programming ability of large multimodal models by integrating visual elements and embedded programming logic.
Thinking Beyond the Local: Multi-View Instructed Adaptive Reasoning in KG-Enhanced LLMs (2026.findings-eacl)

Copied to clipboard

Challenge: Existing methods for large language models adopt query-driven iterative reasoning from a local perspective, limiting efficiency and accuracy for complex multi-hop tasks.
Approach: They propose a multi-view instructed adaptive reasoning of LLM on Knowledge Graphs that allows LLMs to plan, evaluate, and adapt reasoning paths from a global perspective.
Outcome: The proposed model overcomes the limitations of local exploration by enabling LLMs to plan, evaluate, and adapt reasoning paths from a global perspective.
Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Currently, the most commonly used confidence score is the likelihood of the generated sequence . different tokens should be weighted differently depending on the context.
Approach: They propose to assign different weights to various tokens using attention values elicited from the base LLM.
Outcome: The proposed model improves the confidence of the predicted sequence probability by assigning weights to tokens based on attention values elicited from the base model.
Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats (2026.acl-industry)

Copied to clipboard

Challenge: Low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency.
Approach: They evaluate HiFloat (HiF8 and HiF4), a family of floating-point formats tailored for Ascend NPUs.
Outcome: The proposed formats excel with high-variance data and are compatible with state-of-the-art quantization frameworks.
NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model (2025.acl-industry)

Copied to clipboard

Challenge: Existing methods to train a model on a mixture of domain datasets require separate correction language models.
Approach: They propose a multi-task correction MoE that trains experts to become an "expert" of speech-to-text, language-totext and vision-to text datasets by learning to route each dataset’s tokens to its mapped expert.
Outcome: The proposed model outperforms GPT-3.5 and Claude-3.5-Sonnet on the Open ASR Leaderboard and reaches an average relative 5.0% WER reduction and substantial improvements in BLEU scores.

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