Shiao Meng

Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography

Association for Computational Linguistics 2026, Shiao Meng, Yugo Murawaki, Ruiyi Yan

Linguistic steganography based on language models typically assumes that steganographic texts are transmitted without alteration, making them fragile to even minor modifications. While previous work mitigates this fragility by limiting the context window, it significantly compromises text quality. In this paper, we …

cn, jp (code pays fourni par la source)

Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography

Ruiyi Yan, Shiao Meng, Yugo Murawaki

Linguistic steganography based on language models typically assumes that steganographic texts are transmitted without alteration, making them fragile to even minor modifications. While previous work mitigates this fragility by limiting the context window, it significantly compromises text quality. In this paper, we …

Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography

Ruiyi Yan, Shiao Meng, Yugo Murawaki

Linguistic steganography based on language models typically assumes that steganographic texts are transmitted without alteration, making them fragile to even minor modifications. While previous work mitigates this fragility by limiting the context window, it significantly compromises text quality. In this paper, we …

jp (code pays fourni par la source)

Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography

Ruiyi Yan, Shiao Meng, Yugo Murawaki

Linguistic steganography based on language models typically assumes that steganographic texts are transmitted without alteration, making them fragile to even minor modifications.While previous work mitigates this fragility by limiting the context window, it significantly compromises text quality.In this paper, we propose the …

jp, cn (code pays fourni par la source)

GenCNER: A Generative Framework for Continual Named Entity Recognition

Yawen Yang, Fukun Ma, Shiao Meng, Aiwei Liu et autres

Traditional named entity recognition (NER) aims to identify text mentions into pre-defined entity types. Continual Named Entity Recognition (CNER) is introduced since entity categories are continuously increasing in various real-world scenarios. However, existing continual learning (CL) methods for NER face challenges of …

cn (code pays fourni par la source)

GapDNER: A Gap-Aware Grid Tagging Model for Discontinuous Named Entity Recognition

Yawen Yang, Fukun Ma, Shiao Meng, Aiwei Liu et autres

In biomedical fields, one named entity may consist of a series of non-adjacent tokens and overlap with other entities. Previous methods recognize discontinuous entities by connecting entity fragments or internal tokens, which face challenges of error propagation and decoding ambiguity due to …

cn (code pays fourni par la source)

On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations

Shiao Meng, Xuming Hu, Aiwei Liu, Fukun Ma et autres

Driven by the demand for cross-sentence and large-scale relation extraction, document-level relation extraction (DocRE) has attracted increasing research interest. Despite the continuous improvement in performance, we find that existing DocRE models which initially perform well may make more mistakes when merely changing …

On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations

Shiao Meng, Xuming Hu, Aiwei Liu, Fukun Ma et autres

Driven by the demand for cross-sentence and large-scale relation extraction, document-level relation extraction (DocRE) has attracted increasing research interest.Despite the continuous improvement in performance, we find that existing DocRE models which initially perform well may make more mistakes when merely changing the …

cn, hk (code pays fourni par la source)

Prompt Me Up: Unleashing the Power of Alignments for Multimodal Entity and Relation Extraction

Xuming Hu, Junzhe Chen, Aiwei Liu, Shiao Meng et autres

How can we better extract entities and relations from text? Using multimodal extraction with images and text obtains more signals for entities and relations, and aligns them through graphs or hierarchical fusion, aiding in extraction. Despite attempts at various fusions, previous works …

cn, us (code pays fourni par la source)

Prompt Me Up: Unleashing the Power of Alignments for Multimodal Entity and Relation Extraction

Xuming Hu, Junzhe Chen, Aiwei Liu, Shiao Meng et autres

How can we better extract entities and relations from text? Using multimodal extraction with images and text obtains more signals for entities and relations, and aligns them through graphs or hierarchical fusion, aiding in extraction. Despite attempts at various fusions, previous works …

RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction

Shiao Meng, Xuming Hu, Aiwei Liu, Shuang Li et autres

How to identify semantic relations among entities in a document when only a few labeled documents are available? Few-shot document-level relation extraction (FSDLRE) is crucial for addressing the pervasive data scarcity problem in real-world scenarios. Metric-based meta-learning is an effective framework widely …

A Semantic Invariant Robust Watermark for Large Language Models

Aiwei Liu, Leyi Pan, Xuming Hu, Shiao Meng et autres

Watermark algorithms for large language models (LLMs) have achieved extremely high accuracy in detecting text generated by LLMs. Such algorithms typically involve adding extra watermark logits to the LLM's logits at each generation step. However, prior algorithms face a trade-off between attack …