Papers by Chengjin Xu

18 papers
TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation (2020.coling-main)

Copied to clipboard

Challenge: Existing knowledge graphs that contain time information for entities and relations have been used for learning and inference.
Approach: They propose a temporal evolution of entity embedding that defines the temporal rotation from the initial time to the current time in the complex vector space.
Outcome: The proposed model outperforms existing state-of-the-art models for link prediction on three different TKGs.
VLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training (2025.findings-emnlp)

Copied to clipboard

Challenge: a significant drawback of Vision-language Models is their reliance on static training data, leading to outdated information and limited contextual awareness.
Approach: They propose a framework with knowledge-enhanced reranking and noise-injected training to improve the VLM's ranking ability.
Outcome: The proposed framework is based on a simple yet effective instruction template and is able to induce its ranking ability and serve it as a reranker to precisely filter the top-k retrieved images.
Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs (2026.findings-eacl)

Copied to clipboard

Challenge: Existing methods to protect PII from training on small corpora are difficult to implement in real-world applications.
Approach: They propose an entity-based framework that synthesizes encrypted training data to protect PII.
Outcome: The proposed framework outperforms base models and ensures PII security on limited-scale datasets while exhibiting a modest performance gap compared to models trained on unencrypted synthetic data.
LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data (2025.findings-acl)

Copied to clipboard

Challenge: Long-context processing ability has emerged as a significant challenge for large language models.
Approach: They propose a pipeline for synthesizing faithful long-context reasoning instruction datasets . they integrate ground truth and citation-based reasoning prompts integrating them .
Outcome: The proposed pipeline eliminates distractions and improves reasoning chains.
Conflicts Make Large Reasoning Models Vulnerable to Attacks (2026.findings-acl)

Copied to clipboard

Challenge: Large Reasoning Models have demonstrated outstanding capabilities in solving complex reasoning tasks by incorporating step-by-step chain-of-thought (CoT) reasoning.
Approach: They evaluate three large reasoning models that perform explicit and coherent reasoning under conflicting objectives and use them to evaluate their performance.
Outcome: The proposed models perform explicit and coherent reasoning before producing their outputs, improving problem-solving and multi-step decision making.
Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large reasoning models exhibit human-like behaviors such as exploration, verification, reflection, and correction.
Approach: They propose a supervised fine-tuning framework for long chain-of-thoughts reasoning . they leverage a difficulty-aware reward model to estimate the learning value of questions .
Outcome: The proposed framework performs fine-tuning on large reasoning models on 10% of the data selected.
Knowledge Graph Embeddings in Geometric Algebras (2020.coling-main)

Copied to clipboard

Challenge: Existing knowledge graph embedding approaches model entities and relations in KGs using real-valued, complex-value, or hypercomplex-value representations.
Approach: They propose a geometric algebra-based KG embedding framework which uses multivector representations and the geometric product to model entities and relations.
Outcome: The proposed framework outperforms state-of-the-art models for link prediction.
Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion (2025.naacl-long)

Copied to clipboard

Challenge: Existing embedding-based methods rely on triples in the KG, which is vulnerable to specious relation patterns and long-tail entities.
Approach: They propose a context-enriched framework for KGC that uses a large language model to generate potential answers for each query triple.
Outcome: The proposed framework improves on FB15k237 and WN18RR datasets.
Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector Embeddings (2021.naacl-main)

Copied to clipboard

Challenge: Existing knowledge graphs involve evolving data, e.g., the fact (The President of the United States is Barack Obama) is valid only from 2009 to 2017.
Approach: They propose a time-aware knowledge graph embebdding approach which performs 4th-order tensor factorization of a Temporal knowledge graph using a Linear temporal regularizer and Multivector embeddings.
Outcome: The proposed model achieves state-of-the-art performance over four well-established temporal knowledge graph completion benchmarks.
Temporal Extrapolation and Knowledge Transfer for Lifelong Temporal Knowledge Graph Reasoning (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for lifelong TKG reasoning only address part of the challenges.
Approach: They propose a temporal-path-based reinforcement learning framework for lifelong TKG reasoning . they add temporal displacement into the action space of RL to extrapolate for the future .
Outcome: The proposed model outperforms existing models against well-adapted baselines on three lifelong TKG reasoning benchmarks.
Unlocking the Power of Large Language Models for Entity Alignment (2024.acl-long)

Copied to clipboard

Challenge: Entity Alignment (EA) is a crucial step in unifying data from heterogeneous sources and plays a critical role in data-driven AI applications.
Approach: They propose a framework that incorporates large language models to improve EA.
Outcome: The proposed framework incorporates large language models (LLMs) to improve EA accuracy while preserving efficiency.
JudgeAgent: Beyond Static Benchmarks for Knowledge-Driven and Dynamic LLM Evaluation (2026.findings-acl)

Copied to clipboard

Challenge: Current evaluation methods for large language models rely on static benchmarks . limited knowledge coverage and fixed difficulties hinder the targeted optimizations resulting in superficial evaluations of LLMs - a problem that has been addressed by JudgeAgent .
Approach: They propose a knowledge-driven and dynamic evaluation framework for large language models . judgeAgent leverages LLM agents equipped with context graphs to traverse knowledge structures .
Outcome: The proposed framework can achieve comprehensive evaluations and facilitate effective model iterations.
Knowledge Graph Representation Learning using Ordinary Differential Equations (2021.emnlp-main)

Copied to clipboard

Challenge: Knowledge Graph Embeddings (KGEs) map entities and relations from knowledge graphs into a geometric space.
Approach: They propose a neuro differential KGE that embeds nodes of a KG on the trajectories of Ordinary Differential Equations (ODEs) they represent each relation (edge) in a knowledge graph as a vector field on several manifolds.
Outcome: The proposed model can preserve graph characteristics including structural aspects and semantics and avoid wrong inferences.
MM-ChatAlign: A Novel Multimodal Reasoning Framework based on Large Language Models for Entity Alignment (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing MMEA methods rely on knowledge representation learning (KRL) to measure the similarity of entity embeddings.
Approach: They propose a framework that utilizes the visual reasoning abilities of MLLMs for multimodal entity alignment.
Outcome: The proposed framework integrates the visual reasoning abilities of MLLMs for multimodal entity alignment.
Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing financial benchmarks suffer from limited language and task coverage, low-quality datasets, and inadequate adaptability for LLM evaluation.
Approach: They propose a bilingual benchmark for financial LLMs that assesses models’ language understanding and generation capabilities.
Outcome: The proposed bilingual benchmark assesses models’ language understanding and generation capabilities.
Time-aware Graph Neural Network for Entity Alignment between Temporal Knowledge Graphs (2021.emnlp-main)

Copied to clipboard

Challenge: Existing embedding-based approaches disregard time information that exists in many large-scale knowledge graphs, leaving much room for improvement.
Approach: They propose a Time-aware Entity Alignment approach that incorporates relation and time information into a vector space and uses Graph Neural Networks to learn entity representations.
Outcome: The proposed approach outperforms the state-of-the-art methods on real-world TKG datasets due to the inclusion of time information.
DataArc-SynData-Toolkit: A Unified Closed-Loop Framework for Multi-Path, Multimodal, and Multilingual Data Synthesis (2026.acl-demo)

Copied to clipboard

Challenge: Existing synthetic data tools are limited by convoluted workflows, fragmented data standards, and limited scalability across modalities.
Approach: They develop an open-source framework that aims to reduce the technical barrier to synthetic data generation and subsequent model training.
Outcome: The proposed framework achieves an optimal balance between generation efficiency and data quality.
Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Guide-Align is a guideline-oriented approach to augment the safety and quality of Large Language Models.
Approach: They propose a guideline-oriented method to augment the safety and quality of large language models.
Outcome: The proposed method outperforms existing methods on three benchmarks and shows significant improvements in security and quality.

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