Papers by Xiaolong Wei

14 papers
Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning (2022.acl-short)

Copied to clipboard

Challenge: Existing models for TKG reasoning focus on modeling fact sequences of a fixed length, which cannot discover complex evolutional patterns that vary in length.
Approach: They propose to use a length-aware Convolutional Neural Network to handle evolutional patterns of different lengths via an easy-to-difficult curriculum learning strategy.
Outcome: The proposed model improves performance under both offline and online learning strategies.
Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs (2021.acl-long)

Copied to clipboard

Challenge: Temporal Knowledge Graphs (TKGs) are used in many different areas of research.
Approach: They propose to use a beam search policy to induce multiple clues from historical facts . they propose to adopt a graph convolution network based sequence method to deduce answers from clues .
Outcome: The proposed model can predict future facts in two stages, Clue Searching and Temporal Reasoning.
HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning (2022.findings-emnlp)

Copied to clipboard

Challenge: Temporal Knowledge Graphs (TKGs) store facts as triples in the form of subject, relation, object, timestamps.
Approach: They propose a Temporal Knowledge Graph (TKG) model that extends each triple with a timestamp to describe dynamic facts.
Outcome: The proposed model improves on six benchmark datasets with up to 5.6% performance improvement compared to the state-of-the-art models.
Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for enhancing Large Language Models (LLMs) struggle with novelty and Reinforcement Learning from human feedback (RLHF) is costly.
Approach: They propose to use a Reward Model (RM) and a principle-guided LLM-as-a-Judge to enhance creative output over baselines.
Outcome: The proposed approach significantly enhances creative output over baselines, but the principle-guided LLM-as-a-Judge yields superior generation quality.
Few-shot Link Prediction on Hyper-relational Facts (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to predict missing elements in hyper-relational facts require high-quality data.
Approach: They propose a task to predict a missing entity in a hyper-relational fact with limited support instances.
Outcome: The proposed model outperforms existing models on three datasets.
Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns.
Approach: They propose a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory.
Outcome: Experiments on LongMemEval and LoCoMo show that the proposed method outperforms existing methods and achieves up to 12.2% improvement in accuracy.
Inductive Link Prediction in N-ary Knowledge Graphs (2025.coling-main)

Copied to clipboard

Challenge: Existing methods to predict missing elements in NKGs are fixed and therefore cannot be used in real-world situations.
Approach: They propose a task to predict missing elements in unseen facts involving unseent entities and roles in emerging NKGs by embedding unseense entities and role-encoding neural networks.
Outcome: The proposed task outperforms representative models across all datasets.
Improving Text Embeddings with Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for obtaining text embeddings require complex training pipelines . authors leverage proprietary LLMs to generate diverse synthetic data for text embeds based on 93 languages .
Approach: They propose a method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps.
Outcome: The proposed method achieves strong performance on competitive text embedding benchmarks without using any labeled data.
SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval (2023.acl-long)

Copied to clipboard

Challenge: SimLM uses a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training.
Approach: They propose a simple yet effective pre-training method for dense passage retrieval that learns to compress the passage information into a dense vector through self-supervised pre-tuning.
Outcome: The proposed method outperforms multi-vector approaches on large-scale passage retrieval datasets and shows significant improvements over baselines.
FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored.
Approach: They propose to use a benchmark to evaluate large language models' financial domain knowledge and practical abilities.
Outcome: The proposed benchmark evaluates large language models' financial domain knowledge and practical abilities.
Beyond Surface Features: Advancing Medical Vision-Language Alignment via Dynamic Evidence-Guided Preference Optimization (2026.acl-long)

Copied to clipboard

Challenge: Existing preference-based methods for medical large vision-Language Models face limitations in medical settings . existing methods are limited by overfitting to superficial cues and pseudo convergence of the preference signal.
Approach: They propose a framework that enables evidence-aware and adaptive preference learning for Med-LVLMs.
Outcome: The proposed framework improves evidence-aware and adaptive preference learning for Med-LVLMs.
A Survey of Link Prediction in N-ary Knowledge Graphs (2025.emnlp-main)

Copied to clipboard

Challenge: N-ary Knowledge Graphs (NKGs) capture n-ary facts containing more than two entities.
Approach: They present the first comprehensive survey of link prediction in NKGs . they provide an overview of the field and analyze their performance and application scenarios .
Outcome: The proposed methods provide an overview of the field and analyze performance and application scenarios.
UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Existing alignment paradigms for creative writing use static reward signals and supervised data.
Approach: They propose a constraint-aware reward model that synthesizes query-specific criteria to provide fine-grained preference judgments.
Outcome: The proposed framework aligns models with human preferences across content quality and structural paradigms without supervised fine-tuning and ground-truth references.

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