Masaya Ohagi

Takato Yamazaki, Katsumasa Yoshikawa, Toshiki Kawamoto et al.

This paper describes our system submitted to Dialogue Robot Competition 2022. Our proposed system is a combined model of rule-based and generation-based dialog systems. The system utilizes HyperCLOVA, a Japanese foundation model, not only to generate responses but also summarization, search information, etc. We also used our original speech recognition system, which was fine-tuned for this dialog task. As a result, our system ranked second in the preliminary round and moved on to the finals.

Tomoya Mizumoto, Takato Yamazaki, Katsumasa Yoshikawa et al.

When individuals engage in spoken discourse, various phenomena can be observed that differ from those that are apparent in text-based conversation. While written communication commonly uses a question mark to denote a query, in spoken discourse, queries are frequently indicated by a rising intonation at the end of a sentence. However, numerous speech recognition engines do not append a question mark to recognized queries, presenting a challenge when creating a spoken dialogue system. Specifically, the absence of a question mark at the end of a sentence can impede the generation of appropriate responses to queries in spoken dialogue systems. Hence, we investigate the impact of question marks on dialogue systems, with the results showing that they have a significant impact. Moreover, we analyze specific examples in an effort to determine which types of utterances have the impact on dialogue systems.

Masaya Ohagi

Online social networks often create echo chambers where people only hear opinions reinforcing their beliefs. An echo chamber often generates polarization, leading to conflicts caused by people with radical opinions, such as the January 6, 2021, attack on the US Capitol. The echo chamber has been viewed as a human-specific problem, but this implicit assumption is becoming less reasonable as large language models, such as ChatGPT, acquire social abilities. In response to this situation, we investigated the potential for polarization to occur among a group of autonomous AI agents based on generative language models in an echo chamber environment. We had AI agents discuss specific topics and analyzed how the group's opinions changed as the discussion progressed. As a result, we found that the group of agents based on ChatGPT tended to become polarized in echo chamber environments. The analysis of opinion transitions shows that this result is caused by ChatGPT's high prompt understanding ability to update its opinion by considering its own and surrounding agents' opinions. We conducted additional experiments to investigate under what specific conditions AI agents tended to polarize. As a result, we identified factors that strongly influence polarization, such as the agent's persona. These factors should be monitored to prevent the polarization of AI agents.

Pride Kavumba, Koki Wataoka, Huy H. Nguyen et al.

In many practical LLM deployments, a single guardrail is used for both prompt and response moderation. Prompt moderation operates on fully observed text, whereas streaming response moderation requires safety decisions to be made over partial generations. Existing text-based streaming guardrails commonly frame this output-side problem as boundary detection, training models to identify the earliest prefix at which a response has already become unsafe. In this work, we introduce StreamGuard, a unified model-agnostic streaming guardrail that instead formulates moderation as a forecasting problem: given a partial prefix, the model predicts the expected harmfulness of likely future continuations. We supervise this prediction using Monte Carlo rollouts, which enables early intervention without requiring exact token-level boundary annotations. Across standard safety benchmarks, StreamGuard performs strongly both for input moderation and for streaming output moderation. At the 8B scale, StreamGuard improves aggregated input-moderation F1 from 86.7 to 88.2 and aggregated streaming output-moderation F1 from 80.4 to 81.9 relative to Qwen3Guard-Stream-8B-strict. On the QWENGUARDTEST response_loc streaming benchmark, StreamGuard reaches 97.5 F1, 95.1 recall, and 92.6% on-time intervention, compared to 95.9 F1, 92.1 recall, and 89.9% for Qwen3Guard-Stream-8B-stric, while reducing the miss rate from 7.9% to 4.9%. We further show that forecasting-based supervision transfers effectively across tokenizers and model families: with transferred targets, Gemma3-StreamGuard-1B reaches 81.3 response-moderation F1, 98.2 streaming F1, and a 3.5% miss rate. These results show that strong end-to-end streaming moderation can be obtained without exact boundary labels, and that forecasting future risk is an effective supervision strategy for low-latency safety intervention.

Katsumasa Yoshikawa, Takato Yamazaki, Masaya Ohagi et al.

In recent years, large language models (LLMs) have rapidly proliferated and have been utilized in various tasks, including research in dialogue systems. We aimed to construct a system that not only leverages the flexible conversational abilities of LLMs but also their advanced planning capabilities to reduce the speaking load on human interlocutors and efficiently plan trips. Furthermore, we propose a method that divides the complex task of a travel agency into multiple subtasks, managing each as a separate phase to effectively accomplish the task. Our proposed system confirmed a certain level of success by achieving fourth place in the Dialogue Robot Competition 2023 preliminaries rounds. We report on the challenges identified through the competition.