Papers by Ziyang Luo

27 papers
Tree-of-Evolution: Tree-Structured Instruction Evolution for Code Generation in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Data synthesis is a key research area in large language models (LLMs).
Approach: They propose a framework that models code instruction synthesis process with a tree structure and optimization-driven evolution to alleviate constraints of unidirectional synthesis and randomness-driven generation.
Outcome: The proposed framework outperforms open-weight code LLMs on five widely-used benchmarks.
SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on social interactions neglect hallucination while struggling with poor generalizability and implicit character fidelity judgments.
Approach: They propose a generalizable and explicit paradigm for uncovering interactive patterns of Large Language Models across diverse worldviews by defining interactive hallucination through stance transfer and SHARP, a benchmark built by extracting relations from commonsense knowledge graphs.
Outcome: The proposed paradigm is generalizable and explicit and demonstrates its effectiveness and stability.
Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for harmful meme detection ignore in-depth cognition of meme text and image . authors propose a framework for learning reasonable thoughts from LLMs for better multimodal fusion .
Approach: They propose to use large language models to learn reasonable thoughts from LLMs for better multimodal fusion and lightweight fine-tuning.
Outcome: The proposed approach achieves superior performance than state-of-the-art methods on the harmful meme detection task.
CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models (2024.acl-long)

Copied to clipboard

Challenge: Current methods for multimodal sarcasm target identification focus on superficial indicators in an end-to-end manner, overlooking the nuanced understanding of multimodal content.
Approach: They propose a multimodal sarcasm target identification framework with a coarse-to-fine paradigm by augmenting sarcasm explainability with reasoning and pre-training knowledge.
Outcome: The proposed framework outperforms state-of-the-art methods and exhibits explainability in deciphering sarcasm as well.
Conditioned Masked Language and Image Modeling for Image-Text Dense Retrieval (2022.findings-emnlp)

Copied to clipboard

Challenge: Large-scale two-stream pre-trained models like CLIP have achieved tremendous success in image-text retrieval.
Approach: They propose a cross-modal framework for image-text retrieval using two-stream pre-trained models . they embed images and texts into instance representations with two separate encoders . experimental results on MSCOCO and Flickr30k reveal the effectiveness of their framework .
Outcome: The proposed framework improves image-text retrieval performance on two popular cross-modal retrieval benchmarks.
CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding? (2025.coling-main)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have showcased impressive code generation capabilities, primarily evaluated through language-to-code benchmarks.
Approach: They propose a benchmark to assess LLMs’ code understanding abilities from the perspective of code judging rather than code generation.
Outcome: The proposed benchmark evaluates 12 well-known large language models to determine the correctness of provided code solutions.
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.
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.
DecBERT: Enhancing the Language Understanding of BERT with Causal Attention Masks (2022.findings-naacl)

Copied to clipboard

Challenge: Experimental results show that Transformer Encoder model can't automatically capture word order, so explicit position embeddings are required to be fed into the target model.
Approach: They propose a Transformer-based language model DecBERT that uses a causal attention mask to capture word order.
Outcome: The proposed model improves on the GLUE language understanding benchmark and accelerates the pre-training process.
Dialectical Structured Reasoning for Explainable Multimodal Fake News Detection (2026.findings-acl)

Copied to clipboard

Challenge: Existing fake news detection models are opaque and lack deductive transparency . a framework for dialectical structured reasoning is proposed to address this limitation .
Approach: They propose a framework that model fake news detection as an explicit dialectical process over multimodal social context.
Outcome: The proposed framework achieves state-of-the-art while producing transparent explanations that mirror human reasoning process.
MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing evaluation approaches focus on mLLMs’ detection accuracy for binary classification tasks, which often fail to reflect the in-depth interpretive nuance of harmfulness across diverse contexts.
Approach: They propose an agent-based arena-style evaluation framework that provides context-aware and unbiased assessment for mLLMs’ understanding of multimodal harmfulness.
Outcome: The proposed framework reduces evaluation biases of judge agents and provides unbiased comparisons of mLLMs’ abilities to interpret multimodal harmfulness.
A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for fake news detection focus on fact-checked reports, resulting in limited coverage and debunking delays.
Approach: They propose a Coarse-to-fine Cascaded Evidence-Distillation neural network for explainable fake news detection based on raw reports . they use hierarchical encoders and cascaded selectors to select most explainable sentences for verdicts on top of selected top-K reports based upon raw reports.
Outcome: The proposed model outperforms baseline detection methods and generates high-quality explanations from diverse evaluation perspectives.
MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique (2025.findings-emnlp)

Copied to clipboard

Challenge: e MM-CRITIC is a holistic benchmark for evaluating the critique ability of Large Multimodal Models (LMMs) covering 8 main task types and over 500 tasks, covering 4471 samples.
Approach: They introduce a holistic benchmark for evaluating the critique ability of Large Multimodal Models across multiple dimensions: basic, correction, and comparison.
Outcome: The proposed benchmark covers 8 main task types and over 500 tasks and is composed of 4471 samples.
Towards Low-Resource Harmful Meme Detection with LMM Agents (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for harmful meme detection are limited due to the dynamic nature of memes . eliciting knowledge-revising behavior within the LMM agent is a key factor in achieving this goal .
Approach: They propose an agency-driven framework for low-resource harmful meme detection . they use annotated memes to leverage label information as auxiliary signals for model .
Outcome: The proposed framework achieves superior performance than state-of-the-art methods on the low-resource harmful meme detection task.
AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation (2024.emnlp-main)

Copied to clipboard

Challenge: proprietary large language models (LLMs) have demonstrated impressive code generation performance.
Approach: They propose an adaptive module-based model that refines the direct response distillation process by modular decomposition and adaptive response evolution.
Outcome: The proposed framework outperforms baseline model and code generation methods on three popular benchmarks.
DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Chain-of-Thought (CoT) reasoning improves multi-step mathematical problem solving in large language models but is vulnerable to exposure bias and error accumulation.
Approach: They propose a diffusion-styled CoT framework that reformulates CoT reasoning as an iterative denoising process.
Outcome: The proposed framework outperforms existing methods on three multi-step CoT reasoning benchmarks.
KMatrix-2: A Comprehensive Heterogeneous Knowledge Collaborative Enhancement Toolkit for Large Language Model (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing studies on K-LLMs systems focus on declarative knowledge and procedural knowledge (rules) .
Approach: They propose to build a toolkit that supports comprehensive heterogeneous knowledge collaborative enhancement for Large Language Models (LLMs).
Outcome: The proposed toolkit provides unified knowledge integration and joint knowledge retrieval methods to achieve more comprehensive heterogeneous knowledge collaborative enhancement.
Doc-V*: Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA (2026.acl-long)

Copied to clipboard

Challenge: Existing OCR-free approaches to document visual question answering are brittle and passive.
Approach: They propose an OCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
Outcome: The proposed framework outperforms open-source and proprietary models in five benchmarks and improves out-of-domain performance by 47.9% over baseline.
LMR-BENCH: Evaluating LLM Agent’s Ability on Reproducing Language Modeling Research (2025.emnlp-main)

Copied to clipboard

Challenge: Large language model (LLM) agents have demonstrated remarkable potential in advancing scientific discovery, but their capability in reproducing code from research papers remains underexplored.
Approach: They propose to evaluate LLM agents' ability to reproduce scientific research papers by analyzing code reproduction tasks from 23 research papers published in top-tier NLP venues.
Outcome: The proposed benchmark systematically evaluates the capability of large language model (LLM) agents on code reproduction from Language Modeling Research.
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs)-based agents have fundamentally reshaped artificial intelligence . however, the inherent statelessness of LLMs hinders their ability to maintain logical consistency across complex, multi-step tasks .
Approach: They propose a framework for LLM agent memory mechanisms that formalizes the development process into three stages: storage, reflection, and experience.
Outcome: The proposed framework breaks the development process into three stages . it analyzes the need for long-range consistency, challenges in dynamic environments, and the ultimate goal of continual learning.
Have Attention Heads in BERT Learned Constituency Grammar? (2021.eacl-srw)

Copied to clipboard

Challenge: Recent pre-trained language models have gained great success in many tasks, but what they have learned, and when they perform well remain unknown.
Approach: They employ the syntactic distance method to extract implicit constituency grammar from attention weights of attention heads of BERT and RoBERTa.
Outcome: The proposed models induce some grammar types much better than baselines, suggesting some heads act as a proxy for constituency grammar.
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.
MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems (2024.findings-emnlp)

Copied to clipboard

Challenge: Programming often involves translating detailed and complex specifications into code . current state-of-the-art models struggle to solve these problems, a new study shows .
Approach: They propose a multi-modal coding dataset to evaluate algorithmic problem-solving skills in visually rich contexts.
Outcome: The proposed model lacks powerful vision-code models due to the extreme demand for reasoning abilities.
Easy and Efficient Transformer: Scalable Inference Solution For Large NLP Model (2022.naacl-industry)

Copied to clipboard

Challenge: Recent studies show that transformer-based models are effective over many tasks, but they are expensive to deploy in the industrial application.
Approach: They propose a transformer-based inference solution that optimizes kernels for long inputs and large hidden sizes and a flexible CUDA memory manager to reduce the memory footprint when deploying a large model.
Outcome: The proposed solution achieves an average speedup of 1.40-4.20x on the transformer decoder layer with an A100 GPU.
Positional Artefacts Propagate Through Masked Language Model Embeddings (2021.acl-long)

Copied to clipboard

Challenge: Existing word embedding models have a uniform pitfall in assigning a static vector to a word type.
Approach: They propose a neuron-level analysis method to investigate the source of this information by comparing outlier neurons within BERT and RoBERTa’s hidden state vectors.
Outcome: The proposed method pre-trains the RoBERTa-based models and shows that the outliers disappear without positional embeddings.
Aria-UI: Visual Grounding for GUI Instructions (2025.findings-acl)

Copied to clipboard

Challenge: Using a multimodal model, GUI agents can ground from language instructions to target elements . relying on HTML or AXTree inputs is a challenge for GUI agents .
Approach: They propose a large multimodal model specifically designed for GUI grounding that adopts a pure vision approach instead of auxiliary inputs.
Outcome: The proposed model outperforms vision-only and AXTree-reliant models on offline and online agents.

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