Ayana Niwa
Author directory2026
Activation-Level Characterization of Cross-Model Adversarial Jailbreak Transferability in Speech Language Models
Rahaf Alshahrani | Ayana Niwa
Proceedings of the Workshop on Secure, Safe, and Privacy-Preserving Speech and Audio AI (TrustAudio 2026)
Rahaf Alshahrani | Ayana Niwa
Proceedings of the Workshop on Secure, Safe, and Privacy-Preserving Speech and Audio AI (TrustAudio 2026)
Cross-model adversarial jailbreak transferability poses a security challenge for speech-language models (SLMs), as adversarial audio examples generated on one model can remain effective on other architectures. Previous work has shown that transferred attacks against SLMs are feasible, but it remains unclear how transferred adversarial inputs are reflected in the internal representations of different models. We investigate cross-model adversarial jailbreak transferability by combining behavioral evaluation with layer-wise activation analysis across heterogeneous SLMs. Using 386 PGD-based adversarial jailbreak examples provided by SPIRIT that satisfied SPIRIT’s original success criterion on the source model, Qwen2-Audio, we evaluate them on other SLMs without further optimization, revealing substantial differences in behavioral vulnerability across models. Conditional on source-model success, LLaMA-Omni reaches an attack success rate of 98.7% and Qwen2.5-Omni only 2.1%, while 86.5% of the examples also satisfy our stricter criterion on the source model Qwen2-Audio. We further analyze layer wise activation shifts between clean and adversarial inputs in LLaMA-Omni and the source Qwen2-Audio. In both models, activation shifts generally increase toward deeper transformer layers, with the largest changes occurring in the final layers. These findings characterize how adversarial inputs are reflected in internal representations under a cross-model transfer setting.
ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability
Ryuto Koike | Masahiro Kaneko | Ayana Niwa | Preslav Nakov | Naoaki Okazaki
Findings of the Association for Computational Linguistics: ACL 2026
Ryuto Koike | Masahiro Kaneko | Ayana Niwa | Preslav Nakov | Naoaki Okazaki
Findings of the Association for Computational Linguistics: ACL 2026
Detecting texts generated by Large Language Models (LLMs) could cause grave mistakes due to incorrect decisions, such as undermining student’s academic dignity. LLM text detection thus needs to ensure the interpretability of the decision, which can help users judge how reliably correct its prediction is. When humans verify whether a text is human-written or LLM-generated, they intuitively investigate with which of them it shares more similar spans. However, existing interpretable detectors are not aligned with the human decision-making process and fail to offer evidence that users easily understand. To bridge this gap, we introduce ExaGPT, an interpretable detection approach grounded in the human decision-making process for verifying the origin of a text. ExaGPT identifies a text by checking whether it shares more similar spans with human-written vs. with LLM-generated texts from a datastore. This approach can provide similar span examples that contribute to the decision for each span in the text as evidence. Our human evaluation demonstrates that providing similar span examples contributes more effectively to judging the correctness of the decision than existing interpretable methods. Moreover, extensive experiments in four domains and three generators show that ExaGPT massively outperforms prior interpretable detectors by up to +37.0 points of accuracy at a false positive rate of 1%.
Disentangling the Effects of Unlearning in Measuring Parametric Faithfulness of Chain-of-Thought
Ryo Mitsuhashi | Gaku Morio | Ayana Niwa | Masahiro Kaneko | Kentaro Inui | Terufumi Morishita | Yuta Koreeda | Yasuhiro Sogawa
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
Ryo Mitsuhashi | Gaku Morio | Ayana Niwa | Masahiro Kaneko | Kentaro Inui | Terufumi Morishita | Yuta Koreeda | Yasuhiro Sogawa
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
Chain-of-Thought (CoT) in large language models (LLMs) has been widely debated in terms of whether it faithfully reflects an internal reasoning process of models. Parametric faithfulness is a recently proposed metric that uses unlearning to assess whether a model encodes parametric beliefs corresponding to a reasoning chain. This paper refines this metric by accounting for the unintended artifacts of unlearning. We introduce control tasks that unlearn irrelevant knowledge and word-shuffled content and show that these control tasks yield substantial parametric faithfulness values, suggesting the non-negligible effect of unlearning. We also found that control tasks help explain the significant variations in parametric faithfulness observed across different model sizes and CoT lengths. We conclude that the effects of unlearning need to be considered when measuring parametric faithfulness.
Mitigating the Impact of Glitch Tokens via Targeted Retokenization
Muhammad Alif Al Hakim | Dmitrii Kuzmin | Carlos Javier Galán Zavala | Tatsuya Hiraoka | Munachiso Samuel Nwadike | Ayana Niwa | Marco Cognetta | David Pohl | Kentaro Inui
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
Muhammad Alif Al Hakim | Dmitrii Kuzmin | Carlos Javier Galán Zavala | Tatsuya Hiraoka | Munachiso Samuel Nwadike | Ayana Niwa | Marco Cognetta | David Pohl | Kentaro Inui
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
This paper examines whether avoiding undertrained or “glitch” tokens and maximizing tokenization quality during inference can improve downstream task performance without retraining the model. We evaluate this question using a retokenization method that selects the highest-quality tokenization based on the trainedness of tokens, which is defined through the norm or entropy of token embeddings. We compare the performance difference between the tokenization that includes undertrained tokens and the one that avoids such tokens on multiple benchmarks. Our findings reveal a key nuance: undertrained tokens degrade performance primarily when they occupy semantically salient positions that are critical for solving the task. Consequently, retokenization preserves performance on ordinary inputs, while yielding consistent performance improvements when such tokens appear in high-importance contexts.
2025
Rectifying Belief Space via Unlearning to Harness LLMs’ Reasoning
Ayana Niwa | Masahiro Kaneko | Kentaro Inui
Findings of the Association for Computational Linguistics: ACL 2025
Ayana Niwa | Masahiro Kaneko | Kentaro Inui
Findings of the Association for Computational Linguistics: ACL 2025
Large Language Models (LLMs) exhibit sophisticated reasoning yet still generate incorrect answers. We attribute these errors to Spurious Beliefs, defined as propositions the model internally considers as true despite being factually false. To reduce reasoning errors, we propose a belief space rectification framework. Our method first identifies the beliefs invoked during inference via an explanation‐based approach with Forward‐Backward Beam Search (FBBS). We subsequently apply unlearning via gradient ascent to suppress spurious beliefs and enhance true ones, thereby effectively rectifying the model’s belief space. Experiments on three QA datasets and three LLMs show that our method significantly reduces erroneous reasoning and improves generalization.
2024
AmbigNLG: Addressing Task Ambiguity in Instruction for NLG
Ayana Niwa | Hayate Iso
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Ayana Niwa | Hayate Iso
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
2022
Interpretability for Language Learners Using Example-Based Grammatical Error Correction
Masahiro Kaneko | Sho Takase | Ayana Niwa | Naoaki Okazaki
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Masahiro Kaneko | Sho Takase | Ayana Niwa | Naoaki Okazaki
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Grammatical Error Correction (GEC) should not focus only on high accuracy of corrections but also on interpretability for language learning. However, existing neural-based GEC models mainly aim at improving accuracy, and their interpretability has not been explored.A promising approach for improving interpretability is an example-based method, which uses similar retrieved examples to generate corrections. In addition, examples are beneficial in language learning, helping learners understand the basis of grammatically incorrect/correct texts and improve their confidence in writing. Therefore, we hypothesize that incorporating an example-based method into GEC can improve interpretability as well as support language learners. In this study, we introduce an Example-Based GEC (EB-GEC) that presents examples to language learners as a basis for a correction result. The examples consist of pairs of correct and incorrect sentences similar to a given input and its predicted correction. Experiments demonstrate that the examples presented by EB-GEC help language learners decide to accept or refuse suggestions from the GEC output. Furthermore, the experiments also show that retrieved examples improve the accuracy of corrections.
2021
Predicting Antonyms in Context using BERT
Ayana Niwa | Keisuke Nishiguchi | Naoaki Okazaki
Proceedings of the 14th International Conference on Natural Language Generation
Ayana Niwa | Keisuke Nishiguchi | Naoaki Okazaki
Proceedings of the 14th International Conference on Natural Language Generation
We address the task of antonym prediction in a context, which is a fill-in-the-blanks problem. This task setting is unique and practical because it requires contrastiveness to the other word and naturalness as a text in filling a blank. We propose methods for fine-tuning pre-trained masked language models (BERT) for context-aware antonym prediction. The experimental results demonstrate that these methods have positive impacts on the prediction of antonyms within a context. Moreover, human evaluation reveals that more than 85% of predictions using the proposed method are acceptable as antonyms.