Enhancing blocking for entity matching with pre-trained language model and masked autoencoder

BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASR

BaLEEN (Biasing with Latent Encoded Entities), a lightweight, hypernetwork-based framework for dynamic contextual adaptation without fine-tuning the underlying ASR model, is proposed.

LogPISA: An Improved Pre-Training and Tuning Pipeline for Log Understanding With Invariant and Semantic-Aware Objectives

With the rapid development of computer and network technology, network and software logs generated by a multitude of devices contain a wealth of knowledge and serve as a critical resource for intelligent fault diagnosis and efficient system operations. In recent years, various deep learning methods and the pre-training...

Using Self-Improving With Transformers for MSLG-SPA Task

From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation

By thoroughly unifying 36 English hate speech datasets spanning multiple labeling schemes, this work fine-tune a generalist LLM, based on Qwen3 (Qwen Team, 2025), specifically for hate speech mitigation, demonstrating not only state-of-the-art performance on in-domain benchmarks but also substantial improvements in cro...

Optimizing sample selection for large language model-based entity matching using AssistEM

AssistEM, a framework for efficient LLM adaptation to EM via principled data selection, demonstrates that selective fine-tuning not only accelerates adaptation but also improves training efficiency (requiring fewer GPU hours), enabling open-source LLMs to rival–and in some cases outperform–closed-source models.

Location-Aware Language Models via Secondary Embeddings

This work proposes a lightweight, model-agnostic approach for injecting geo-spatial awareness into pretrained embeddings without modifying the tokenizer or requiring costly retraining, and generalizes across multiple model architectures and scales.