Yugo Murawaki

HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Framework

Ruiyi Yan, Zhongliang Yang, Yugo Murawaki

Generative linguistic steganography conceals secret bits within the sampling randomness of large language models. Existing schemes are single-stream, conveying an entire secret through a single response to a single prompt. This convention incurs limitations: it provides no protocol-level support for batched multi-stream …

HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Framework

Ruiyi Yan, Zhongliang Yang, Yugo Murawaki

Generative linguistic steganography conceals secret bits within the sampling randomness of large language models. Existing schemes are single-stream, conveying an entire secret through a single response to a single prompt. This convention incurs limitations: it provides no protocol-level support for batched multi-stream …

cn, jp (code pays fourni par la source)

Dango: A Strictly L1-Only Large Language Model for Studying Second Language Acquisition

Shiho Matta, Yin Jou Huang, Fei Cheng, Takashi Kodama et autres

We introduce Dango, a 1.8B-parameter large language model designed for controlled studies of L1-to-L2 (Japanese-to-English) transfer in second language acquisition (SLA). While previous studies have explored SLA in language models, they have predominantly relied on smaller or non-decoder models, limiting their ability …

Dango: A Strictly L1-Only Large Language Model for Studying Second Language Acquisition

Shiho Matta, Yin Jou Huang, Fei Cheng, Takashi Kodama et autres

We introduce Dango, a 1.8B-parameter large language model designed for controlled studies of L1-to-L2 (Japanese-to-English) transfer in second language acquisition (SLA). While previous studies have explored SLA in language models, they have predominantly relied on smaller or non-decoder models, limiting their ability …

jp, in (code pays fourni par la source)

Scaling LLM Reasoning from Minimal Labels: A Semi-Supervised Framework with a Lightweight Verifier

Keizo Kato, Chenhui Chu, Yugo Murawaki, Sado Kurohashi

For the development of Large language models (LLMs), recent approaches to generating pseudo intermediate reasoning have shown remarkable progress. But they typically rely on large numbers of correctly annotated answers to assess reasoning quality. This paper presents a semi-supervised framework that scales …

Scaling LLM Reasoning from Minimal Labels: A Semi-Supervised Framework with a Lightweight Verifier

Keizo Kato, Chenhui Chu, Yugo Murawaki, Sado Kurohashi

For the development of Large language models (LLMs), recent approaches to generating pseudo intermediate reasoning have shown remarkable progress. But they typically rely on large numbers of correctly annotated answers to assess reasoning quality. This paper presents a semi-supervised framework that scales …

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)

Efficient Provably Secure Linguistic Steganography via Range Coding

Ruiyi Yan, Yugo Murawaki

Linguistic steganography involves embedding secret messages within seemingly innocuous texts to enable covert communication. Provable security, which is a long-standing goal and key motivation, has been extended to language-model-based steganography. Previous provably secure approaches have achieved perfect imperceptibility, measured by zero Kullback-Leibler …

Efficient Provably Secure Linguistic Steganography via Range Coding

Ruiyi Yan, Yugo Murawaki

Linguistic steganography involves embedding secret messages within seemingly innocuous texts to enable covert communication. Provable security, which is a long-standing goal and key motivation, has been extended to language-model-based steganography. Previous provably secure approaches have achieved perfect imperceptibility, measured by zero Kullback-Leibler …

jp (code pays fourni par la source)

Developing a Compute-Intensive Bayesian Statistical Model for Reinterpreting Phylogenetic Trees as Geographical Distributions

Yugo Murawaki

Persona Jailbreaking in Large Language Models

Association for Computational Linguistics 2026, Fei Cheng, Yugo Murawaki, Jivnesh Sandhan et autres

Large Language Models (LLMs) are increasingly deployed in domains such as education, mental health and customer support, where stable and consistent personas are critical for reliability. Yet, existing studies focus on narrative or role-playing tasks and overlook how adversarial conversational history alone …

jp (code pays fourni par la source)