arXiv subjects

Binwei Yao

Publications and source records attributed to Binwei Yao.

9 recordsLinked to original sources

arXiv2026

Whose Values Are Generated? Measuring Visual Value Leakage in Multilingual Text-to-Image Generation

Text-to-image (T2I) systems serve users across languages and cultural contexts. However, evaluations of cultural representation focus mainly on recognizable elements such as landmarks, clothing, and activities, overlooking the cultural values that generated images convey. To bridge this gap, we introduce VisionValueBench, a multilingual benchmark that operationalizes six of Hofstede's cultural value dimensions (e.g., individualism versus collectivism) to investigate how T2I systems frame neutral social situations through a particular cultural orientation. We find that value-neutral prompts, which admit diverse cultural interpretations, nonetheless yield images that favor particular value orientations, a phenomenon we call visual value leakage. We evaluate prompts varying in language and geographic cues across 960 social scenarios and six T2I configurations. Generated images consistently favor the same value orientations across all six dimensions, for example, equality over hierarchy (low power distance), individual autonomy over group obligation (individualism), and enjoyment over restraint (indulgence). Prompt language has limited influence on these orientations, whereas geographic cues shift some dimensions toward the associated cultural values while largely preserving the prevailing orientations. These findings reveal substantial homogeneity in the cultural values conveyed by T2I systems worldwide.

cs.CV↗

arXiv2026

DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents

Modeling opinion change through social interactions is important for understanding polarization, misinformation, and societal conflict. Recent work simulates opinion dynamics with role-playing LLM agents (RPLAs), but multi-agent simulations often display unnatural group behavior (e.g., premature convergence) and lack empirical benchmarks for assessing alignment with real human group interactions. We introduce DEBATE, a benchmark for evaluating the authenticity of opinion dynamics in multi-agent RPLA simulations. DEBATE contains multi-round public messages and private Likert-scale beliefs from U.S.-based participants across 107 topics; the cleaned benchmark used in our experiments contains 2,788 participants in 697 groups, enabling evaluation at the utterance and group levels. We instantiate digital-twin RPLAs with seven LLMs and evaluate across two settings: next-message prediction and full dynamics simulation, using stance-based opinion-dynamics metrics. In zero-shot settings, RPLA groups exhibit strong opinion convergence relative to human groups. Across group-generalization tests with unseen participant groups and topic-generalization tests with unseen discussion topics, supervised fine-tuning (SFT) for Llama-3.1-8B-Instruct improves stance prediction of individuals and convergence prediction at the group level, though discrepancies in opinion change and belief updating remain. The dataset and benchmark website are publicly available.

cs.CL↗

arXiv2026

SITA: Learning Speaker-Invariant and Tone-Aware Speech Representations for Low-Resource Tonal Languages

Tonal low-resource languages are widely spoken but remain underserved by modern speech technologies. A central challenge is learning speech representations that are robust to nuisance variation, such as speaker gender, while preserving lexical tone, which carries word meaning. We propose SITA, a lightweight adaptation recipe for pretrained wav2vec-style self-supervised speech encoders. Rather than designing a new backbone or objective, SITA combines existing objectives in a staged optimization framework to reduce tone collapse while preserving ASR capability. Stage 1 improves speaker invariance without erasing tonal contrasts by combining a cross-gender contrastive loss with a tone-repulsive loss that separates same-word, different-tone realizations. Stage 2 restores recognition-oriented linguistic information through CTC fine-tuning and knowledge distillation on upper encoder layers. We evaluate SITA primarily on Hmong, a tonal language with limited digital resources and a small speaker pool. Against multilingual, speaker-adversarial, label-aware, and semi-supervised baselines, SITA achieves the best trade-off between cross-gender lexical retrieval and tone separation, while maintaining ASR accuracy close to an ASR-adapted XLS-R teacher. Results on Mandarin show consistent gains, suggesting that SITA is a general plug-in recipe for tonal speech representation learning.

cs.CL↗

arXiv2025

Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate

Large language models (LLMs) often display sycophancy, a tendency toward excessive agreeability. This behavior poses significant challenges for multi-agent debating systems (MADS) that rely on productive disagreement to refine arguments and foster innovative thinking. LLMs' inherent sycophancy can collapse debates into premature consensus, potentially undermining the benefits of multi-agent debate. While prior studies focus on user--LLM sycophancy, the impact of inter-agent sycophancy in debate remains poorly understood. To address this gap, we introduce the first operational framework that (1) proposes a formal definition of sycophancy specific to MADS settings, (2) develops new metrics to evaluate the agent sycophancy level and its impact on information exchange in MADS, and (3) systematically investigates how varying levels of sycophancy across agent roles (debaters and judges) affects outcomes in both decentralized and centralized debate frameworks. Our findings reveal that sycophancy is a core failure mode that amplifies disagreement collapse before reaching a correct conclusion in multi-agent debates, yields lower accuracy than single-agent baselines, and arises from distinct debater-driven and judge-driven failure modes. Building on these findings, we propose actionable design principles for MADS, effectively balancing productive disagreement with cooperation in agent interactions.

cs.CL↗

arXiv2025

AI as a deliberative partner fosters intercultural empathy for Americans but fails for Latin American participants

Despite increasing AI chatbot deployment in public discourse, empirical evidence on their capacity to foster intercultural empathy remains limited. Through a randomized experiment, we assessed how different AI deliberation approaches--cross-cultural deliberation (presenting other-culture perspectives), own-culture deliberation (representing participants' own culture), and non-deliberative control--affect intercultural empathy across American and Latin American participants. Cross-cultural deliberation increased intercultural empathy among American participants through positive emotional engagement, but produced no such effects for Latin American participants, who perceived AI responses as culturally inauthentic despite explicit prompting to represent their cultural perspectives. Our analysis of participant-driven feedback, where users directly flagged and explained culturally inappropriate AI responses, revealed systematic gaps in AI's representation of Latin American contexts that persist despite sophisticated prompt engineering. These findings demonstrate that current approaches to AI cultural alignment--including linguistic adaptation and explicit cultural prompting--cannot fully address deeper representational asymmetries in AI systems. Our work advances both deliberation theory and AI alignment research by revealing how the same AI system can simultaneously promote intercultural understanding for one cultural group while failing for another, with critical implications for designing equitable AI systems for cross-cultural democratic discourse.

cs.HC↗

arXiv2025

No Preference Left Behind: Group Distributional Preference Optimization

Preferences within a group of people are not uniform but follow a distribution. While existing alignment methods like Direct Preference Optimization (DPO) attempt to steer models to reflect human preferences, they struggle to capture the distributional pluralistic preferences within a group. These methods often skew toward dominant preferences, overlooking the diversity of opinions, especially when conflicting preferences arise. To address this issue, we propose Group Distributional Preference Optimization (GDPO), a novel framework that aligns language models with the distribution of preferences within a group by incorporating the concept of beliefs that shape individual preferences. GDPO calibrates a language model using statistical estimation of the group's belief distribution and aligns the model with belief-conditioned preferences, offering a more inclusive alignment framework than traditional methods. In experiments using both synthetic controllable opinion generation and real-world movie review datasets, we show that DPO fails to align with the targeted belief distributions, while GDPO consistently reduces this alignment gap during training. Moreover, our evaluation metrics demonstrate that GDPO outperforms existing approaches in aligning with group distributional preferences, marking a significant advance in pluralistic alignment.

cs.CL↗

arXiv2024

Benchmarking Machine Translation with Cultural Awareness

Translating culture-related content is vital for effective cross-cultural communication. However, many culture-specific items (CSIs) often lack viable translations across languages, making it challenging to collect high-quality, diverse parallel corpora with CSI annotations. This difficulty hinders the analysis of cultural awareness of machine translation (MT) systems, including traditional neural MT and the emerging MT paradigm using large language models (LLM). To address this gap, we introduce a novel parallel corpus, enriched with CSI annotations in 6 language pairs for investigating Culturally-Aware Machine Translation--CAMT. Furthermore, we design two evaluation metrics to assess CSI translations, focusing on their pragmatic translation quality. Our findings show the superior ability of LLMs over neural MTs in leveraging external cultural knowledge for translating CSIs, especially those lacking translations in the target culture.

cs.CL↗

arXiv2024

Towards Reliable and Empathetic Depression-Diagnosis-Oriented Chats

Chatbots can serve as a viable tool for preliminary depression diagnosis via interactive conversations with potential patients. Nevertheless, the blend of task-oriented and chit-chat in diagnosis-related dialogues necessitates professional expertise and empathy. Such unique requirements challenge traditional dialogue frameworks geared towards single optimization goals. To address this, we propose an innovative ontology definition and generation framework tailored explicitly for depression diagnosis dialogues, combining the reliability of task-oriented conversations with the appeal of empathy-related chit-chat. We further apply the framework to D$^4$, the only existing public dialogue dataset on depression diagnosis-oriented chats. Exhaustive experimental results indicate significant improvements in task completion and emotional support generation in depression diagnosis, fostering a more comprehensive approach to task-oriented chat dialogue system development and its applications in digital mental health.

cs.AI↗

arXiv2022

D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat

In a depression-diagnosis-directed clinical session, doctors initiate a conversation with ample emotional support that guides the patients to expose their symptoms based on clinical diagnosis criteria. Such a dialogue system is distinguished from existing single-purpose human-machine dialog systems, as it combines task-oriented and chit-chats with uniqueness in dialogue topics and procedures. However, due to the social stigma associated with mental illness, the dialogue data related to depression consultation and diagnosis are rarely disclosed. Based on clinical depression diagnostic criteria ICD-11 and DSM-5, we designed a 3-phase procedure to construct D$^4$: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat, which simulates the dialogue between doctors and patients during the diagnosis of depression, including diagnosis results and symptom summary given by professional psychiatrists for each conversation. Upon the newly-constructed dataset, four tasks mirroring the depression diagnosis process are established: response generation, topic prediction, dialog summary, and severity classification of depressive episode and suicide risk. Multi-scale evaluation results demonstrate that a more empathy-driven and diagnostic-accurate consultation dialogue system trained on our dataset can be achieved compared to rule-based bots.

cs.CL↗