Papers by Wei Ju

19 papers
HEAL: Hybrid Enhancement with LLM-based Agents for Text-attributed Hypergraph Self-supervised Representation Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to enhance text-attributed hypergraph self-supervised learning are limited by label scarcity.
Approach: They propose a data-centric approach that leverages large language models to enhance hypergraph self-supervised learning by integrating hyperedges into a self-representation framework.
Outcome: The proposed approach generates informative nodes and hyperedges through multi-round interaction with LLM-based agents.
A Survey on Efficient Large Language Model Training: From Data-centric Perspectives (2025.acl-long)

Copied to clipboard

Challenge: achieving data-efficient post-training of Large Language Models is a key research question.
Approach: They propose a taxonomy of data-efficient LLM post-training methods from a data-centric perspective.
Outcome: The proposed methods cover data selection, data quality enhancement, synthetic data generation, data distillation and compression, and self-evolving data ecosystems.
ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for fine-tuning-based compression suffer from verbose outputs, increasing computational overhead.
Approach: They propose a framework to generate concise reasoning chains using Confidence Injection and Early Stopping.
Outcome: The proposed framework reduces the length of the model by up to 50% while maintaining high task accuracy.
UOR: Universal Backdoor Attacks on Pre-trained Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods to attack pre-trained language models rely on manual selection of triggers and backdoor representations.
Approach: They propose a backdoor attack method that turns manual selection into automatic optimization . they propose to use poisoned contrastive learning to learn more uniform backdoor representations .
Outcome: The proposed method achieves better attack performance on text classification tasks compared to manual methods.
Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Recent work has demonstrated the power of large language models in recalling knowledge and reasoning.
Approach: They propose to erase shortcut neurons to mitigate the associated risks . 20% of the failures are attributed to shortcuts, they find .
Outcome: The proposed approach reduces failures in multi-hop knowledge editing caused by shortcuts by 20% .
Backdoor NLP Models via AI-Generated Text (2024.lrec-main)

Copied to clipboard

Challenge: Existing attacks disregard fluency and semantic fidelity of poisoned text, rendering it easily detectable.
Approach: They propose to use AI-generated poisoned text to attack NLP models by establishing covert associations between trigger patterns and target labels without affecting normal accuracy.
Outcome: The proposed method achieves effective attacks while maintaining fluency and semantic similarity across all scenarios.
Embracing Large Language Models in Traffic Flow Forecasting (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to predict future traffic flows capture spatio-temporal dependencies, but they fail to adapt to test-time environmental changes.
Approach: They propose to use large language models to help traffic flow forecasting by capturing spatio-temporal dependencies and using a large language model to select the most likely result.
Outcome: The proposed method is based on large language models (LLMs) and an LLM-based selector.
IRRGN: An Implicit Relational Reasoning Graph Network for Multi-turn Response Selection (2022.emnlp-main)

Copied to clipboard

Challenge: Existing studies focus on matching between candidate options and historical dialogues while ignoring the reasoning ability of the model.
Approach: They propose an Implicit Relational Reasoning Graph Network to address these issues . they propose to implicitly extract dependencies between utterances and options .
Outcome: The proposed model outperforms human models on two multi-turn dialogue reasoning benchmark datasets.
Calibrating Inference Time Alignment with Sequence-level Risk Accumulation (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to decode large language models (LLMs) often over-reject benign information, limiting their generalizability in real-world scenarios where harmful and benign information coexist.
Approach: They propose a framework to regulate decoding alignments for Large Language Models (LLMs) they employ a reward-guided branch decoding paradigm to incorporate safety awareness during generation.
Outcome: The proposed framework achieves superior performance on four attack benchmarks and two neutral datasets.
PED: Route-Decoupled Diagnostics for Persona Consistency in Spoken Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing evaluations of persona-emotion decoupling frameworks do not isolate which component caused the failure . current evaluations do little to isolate the cause of the failure, making fixes slow and ad hoc .
Approach: They propose a diagnostic evaluation framework that decomposes persona expression into two observable routes.
Outcome: The proposed framework decomposes persona expression into two observable routes . it can be used to perform route-comparable, reference-based analyses of separability, drift, failures and coupling .
UER: An Open-Source Toolkit for Pre-training Models (D19-3)

Copied to clipboard

Challenge: Existing work on pre-training models have shown that it is important to use a framework to deploy various pre- training models efficiently.
Approach: They propose an assemble-on-demand pre-training toolkit that assembles pre-trained models on demand and encapsulates them with rich modules.
Outcome: The proposed framework can reproduce state-of-the-art models or develop models that remain unexplored.
CoTrust: Privacy-Preserving Collaboration Between Large and Small Language Models in Trusted Execution Environments (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) provide powerful text generation capabilities, but accessing sensitive user inputs raises privacy concerns.
Approach: They propose a privacy-preserving collaborative inference framework that combines large language models with small language models inside TEE to preserve privacy.
Outcome: Experiments show that CoTrust outperforms unconstrained LLMs on multiple question answering and summarization benchmarks while maintaining strong privacy protection.
LEAF: Large Language Diffusion Model for Time Series Forecasting (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent work has applied large language models (LLMs) into time series forecasting, but they lack an understanding of holistic temporal patterns with potential error accumulation.
Approach: They propose a framework that marries Larg e Langu age Diffusion Model with time series forecasting (LEAF) they propose converting time series into tokens and adopting language diffusion models to capture temporal dependencies.
Outcome: The proposed framework generates future predictions with a diffusion model from a holistic view.
Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness (2025.findings-emnlp)

Copied to clipboard

Challenge: Multi-modal large language models have been used for processing and understanding information from diverse modalities.
Approach: They propose to evaluate the audio-visual capabilities of multi-modal large language models . they focus on effectiveness, efficiency, generalizability, and robustness .
Outcome: The proposed models exhibit strong zero-shot and few-shot generalization abilities . their success relies heavily on the vision modality, which impairs performance when visual input is corrupted or missing.
How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies have focused on enhancing the factualness of large language models using context knowledge.
Approach: They propose to use ChatGPT to construct probing datasets that provide diverse and coherent evidence corresponding to various facts.
Outcome: The proposed model can encode knowledge across different layers, and it is compared with existing models.
E-ViC: Reasoning Beyond Text via Embodied Visual Chain for Spatial Intelligence (2026.acl-long)

Copied to clipboard

Challenge: Existing Vision-Language Models (VLMs) lack spatial reasoning, despite text-based CoTs . e-ViC reframes spatial intelligence as a verifiable, tool-using capability, argues a new study.
Approach: They propose a framework that moves reasoning beyond text into the visual domain . they ground reasoning in pixel-level interactions to enable human-like "look-and-confirm" strategies .
Outcome: The proposed framework outperforms existing Vision-Language Models with an average gain of 10.1%.
Semi-supervised Fine-tuning for Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Existing LLMs require labeled data, which can be costly in real-world applications.
Approach: They propose a framework that can fully exploit labeled and unlabeled data for LLM fine-tuning . they conducted experiments using GPT-4o-mini and Llama-3.1 on seven general or domain-specific datasets .
Outcome: The proposed framework can fully exploit labeled and unlabeled data for LLM alignment from a propagate-and-select manner.
MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation (2025.naacl-long)

Copied to clipboard

Challenge: Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, but many benchmarks suffer from systematic biases.
Approach: They propose a benchmark to avoid Type-I errors by creating one perception question and one knowledge anchor question through a meticulous annotation process.
Outcome: The proposed benchmark avoids Type-I errors while maintaining reliability of MCQ evaluations.
DANCE: Diversity-attended Dynamic Caching with Asymmetric Quantization for Test-time Adaptation of Vision-Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to test-time adaptation of vision-language models measure prediction entropy but these samples tend to approach prototypes with limited coverage of data distributions.
Approach: They propose a new approach for test-time adaptation of vision-language models . they construct a dynamic cache to store diversity-aware test samples .
Outcome: The proposed approach is more efficient than current methods on augmented visual models.

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