Xinyan Yu

Jungo Kasai, Keisuke Sakaguchi, Yoichi Takahashi et al. · allen-ai, uw

We introduce REALTIME QA, a dynamic question answering (QA) platform that announces questions and evaluates systems on a regular basis (weekly in this version). REALTIME QA inquires about the current world, and QA systems need to answer questions about novel events or information. It therefore challenges static, conventional assumptions in open-domain QA datasets and pursues instantaneous applications. We build strong baseline models upon large pretrained language models, including GPT-3 and T5. Our benchmark is an ongoing effort, and this paper presents real-time evaluation results over the past year. Our experimental results show that GPT-3 can often properly update its generation results, based on newly-retrieved documents, highlighting the importance of up-to-date information retrieval. Nonetheless, we find that GPT-3 tends to return outdated answers when retrieved documents do not provide sufficient information to find an answer. This suggests an important avenue for future research: can an open-domain QA system identify such unanswerable cases and communicate with the user or even the retrieval module to modify the retrieval results? We hope that REALTIME QA will spur progress in instantaneous applications of question answering and beyond.

Russian, Wu, Tim Moesgen et al.

With growing research on haptic interfaces, Mediated Social Touch (MST) technologies offer the potential to record, synthesise, and reproduce (RSR) touch experiences across space and time, enabling, for instance, a hug from afar and from the past. Although much of the existing research highlights the direct benefits of these systems, such as reducing loneliness and providing emotional support, little attention has been paid to their broader sociotechnical impacts. To address this gap, we used the Future Ripples method to speculate on possible effects of MST. We conducted three workshops with 24 participants, including potential users, domain experts, and haptics researchers. Throughout these sessions, participants collectively envisioned possible future scenarios, alongside opportunities and threats, and proposed actionable responses. Our qualitative analysis organised these insights into four themes and three distinctive challenges. These findings offer haptics researchers intervention points across the RSR pipeline to inform MST design, alongside methodological insights from applying Future Ripples to MST technology.

Xinyan Yu, Marius Hoggenmueller, Xin Lu et al.

Urban HCI investigates how digital technologies shape human behaviour within the social, spatial, temporal dynamics of public space. Meanwhile, robotic furniture research demonstrates how the purposeful animation of mundane utilitarian elements can influence human behaviour in everyday contexts. Taken together, these strands highlight an untapped opportunity to investigate how animated public furniture could mediate social interaction in urban environments. In this paper, we present the design process and in-the-wild study of mobile robotic benches that reconfigure with a semi-outdoor public space. Our findings show that the gestural performance of the benches manifested three affordances perceived by passersby, they activated engagement as robots, redistributed engagement as spatial elements, and settled engagement as infrastructure. We proposed an Affordance Transition Model (ATM) describing how robotic furniture could proactively facilitate transition between these affordances to engage passersby. Our study bridges robotic furniture and urban HCI to activate human experience with the built environment purposefully.

Xinyan Yu, Marius Hoggenmueller, Tram Thi Minh Tran et al.

Emerging technologies introduce sociotechnical tensions that call for closer collaboration between technology design and policy. In this work, we introduce Design-Policy Adversarial Futuring, a scenario-based workshop method that supports design-policy engagement by structuring contestation between design and policy perspectives. We report on a workshop conducted in the autonomous mobility domain with 12 HCI researchers, used to explore and demonstrate the method in practice. The workshop illustrates how the adversarial futuring method can surface shifting harms, translate policy abstractions into situated use, and legitimise extreme ideas while maintaining grounded policy reasoning. This work contributes a reusable, exploratory method for supporting HCI-policy collaboration through contestation, which can be adapted across emerging technological domains.

Yuntai Bao, Qinfeng Li, Xinyan Yu et al.

Recently, steering vectors (SVs) have emerged as an effective and lightweight approach to steer behaviors of large language models (LLMs), among which fine-tuned SVs are more effective than optimization-free ones. However, current approaches to fine-tuned SVs suffer from two limitations. First, they require careful selection of steering factors on a per-SV basis to balance steering effectiveness and generation quality at inference time. Second, they operate as full-sequence SVs (FSSVs), which can sacrifice generation quality regardless of factor selection due to excessive intervention on the model generation process. To address the first limitation, we propose joint training of steering factors and directions, such that post-hoc factor selection is no longer required. Using neural network scaling theory, we find that moderately large initialization sizes and learning rates for steering factors are essential for stability and efficiency of joint training. To tackle the second limitation, we draw inspiration from representation fine-tuning and introduce Prompt-only SV (PrOSV), an SV that intervenes only on a few prompt tokens. Our empirical results show that PrOSV outperforms traditional FSSVs on AxBench when using our joint training scheme. We also find that PrOSV achieves a better tradeoff between general model utility and adversarial robustness than FSSV.

Akari Asai, Xinyan Yu, Jungo Kasai et al.

We present Cross-lingual Open-Retrieval Answer Generation (CORA), the first unified many-to-many question answering (QA) model that can answer questions across many languages, even for ones without language-specific annotated data or knowledge sources. We introduce a new dense passage retrieval algorithm that is trained to retrieve documents across languages for a question. Combined with a multilingual autoregressive generation model, CORA answers directly in the target language without any translation or in-language retrieval modules as used in prior work. We propose an iterative training method that automatically extends annotated data available only in high-resource languages to low-resource ones. Our results show that CORA substantially outperforms the previous state of the art on multilingual open QA benchmarks across 26 languages, 9 of which are unseen during training. Our analyses show the significance of cross-lingual retrieval and generation in many languages, particularly under low-resource settings.