Multimodal Large Language Models (MLLMs) are increasingly deployed as social agents, yet their ability to integrate conflicting identity cues remains underexplored. We audit gender bias in ten recent MLLMs using a counterfactual cooperative gaming task that pairs synthetic voices with avatars of varying gender presentation and visual fidelity. Our analysis reveals distinct bias patterns that can occur independently: closed-source models (e.g., Gemini 2.5/3) exhibit a near-deterministic “voice-matching” bias that enforces binary alignment between voice and appearance, whereas open-weight models (e.g., Qwen-2.5-Omni-7B) show limited responsiveness to vocal cues and instead exhibit context-driven stereotypes, such as preferring male avatars in combat scenarios. We further find that reducing visual realism attenuates matching tendencies in some models. These findings demonstrate that multimodal fairness is not monolithic; models may appear unbiased on one dimension while enforcing strict identity congruence or role-based stereotypes on another. Code and data are available at https://github.com/halfhoon/whose-voice-whose-avatar.

The transition to end-to-end Multimodal Large Language Models (MLLMs) has positioned these architectures as active social evaluators in high-stakes domains. However, it remains unclear whether these models maintain objective auditory perception or succumb to the "Hearing with Eyes" phenomenon, where visual racial cues distort linguistic proficiency evaluations. We investigate this cross-modal bias by constructing a controlled counterfactual dataset utilizing a Visual Matched-Guise Paradigm. By pairing identical native audio with diverse visual personas across English and Korean contexts, we reveal a distinct Cultural Asymmetry in model behavior. In Anglophone settings, most closed models exhibit Reverse Linguistic Stereotyping, hallucinating non-native accents for Asian speakers despite standard native audio. Conversely, in Korean settings, the same models assign baseline-relative competence premiums across all visual personas, with the largest gains for out-group (White/Black) speakers, consistent with Expectancy Violation Theory. Our findings demonstrate that MLLMs do not merely process sensory inputs but actively reproduce context-dependent sociolinguistic ideologies.

As people increasingly turn to AI for personal deliberation beyond task-oriented assistance, concerns about sycophancy in these value-laden contexts have grown. Unlike human flattery, which is intentional and self-interested, AI sycophancy emerges as a byproduct of RLHF’s reward structure for user-preference alignment. Yet the observable behavior is similar: both produce responses that preserve what users want to hear. Focusing on this phenomenon through Goffman’s face-work framework, we operationalize AI sycophancy as excessive face-saving, either active (preserving positive face through agreement) or passive (preserving negative face by withholding challenge). In a mixed-methods study (N=31), participants engaged with AI across three moral dilemmas under these conditions and a non-sycophantic neutral baseline. Sycophantic responses increased decision confidence but reduced open-minded thinking; participants felt supported yet found the conversations unproductive. Neutral responses, though initially uncomfortable, promoted cognitive flexibility and meaningful deliberation. These findings reveal a confidence-competence trade-off in AI-mediated moral reasoning and suggest that effective AI for personal deliberation requires calibrated friction, not unconditional agreement.

Recent Large Audio-Language Models (LALMs) integrate acoustic capabilities into reasoning, yet whether they reliably ground clinical judgments in audible evidence remains unproven. We introduce CliniCAST (Clinical Controlled Acoustic Synthetic Triage), a controlled benchmark that disentangles clinically meaningful acoustic cues from lexical content and speaker demographics. CliniCAST comprises 5,856 synthetic samples across 12 disease conditions: 4,800 audio samples forming 2,400 tagged–untagged pairs for five-level emergency triage, and 1,056 audio–text inconsistent samples in which reassuring speech is paired with high-risk acoustic cues. Evaluating a diverse suite of audio-capable foundation models, we find that LALMs exhibit fragile acoustic grounding and a pronounced “text dominance” failure mode: reassuring lexical content suppresses response to audible distress signals even under safety-critical conditions. Age and gender interactions are weak across conditions, indicating that the primary failure mode is insufficient cross-modal integration rather than demographic bias. These results suggest current LALMs are not yet robust enough for high-stakes medical triage, and motivate training objectives that explicitly enforce reliance on clinically grounded audible evidence.

Existing function-calling benchmarks focus on single-turn interactions. However, they overlook the complexity of real-world scenarios. To quantify how existing benchmarks address practical applications, we introduce DICE-SCORE, a metric that evaluates the dispersion of tool-related information such as function name and parameter values throughout the dialogue. Analyzing existing benchmarks through DICE-SCORE reveals notably low scores, highlighting the need for more realistic scenarios. To address this gap, we present DICE-BENCH, a framework that constructs practical function-calling datasets by synthesizing conversations through a tool graph that maintains dependencies across rounds and a multi-agent system with distinct personas to enhance dialogue naturalness. The final dataset comprises 1,607 high-DICE-SCORE instances. Our experiments on 19 LLMs with DICE-BENCH show that significant advances are still required before such models can be deployed effectively in real-world settings. Our code and data are all publicly available.

This study investigates the halo effect in AI-driven hiring evaluations using Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Through experiments with hypothetical job applications, we examined how these models’ evaluations are influenced by non-job-related information, including extracurricular activities and social media images. By analyzing models’ responses to Likert-scale questions across different competency dimensions, we found that AI models exhibit significant halo effects, particularly in image-based evaluations, while text-based assessments showed more resistance to bias. The findings demonstrate that supplementary multimodal information can substantially influence AI hiring decisions, highlighting potential risks in AI-based recruitment systems.

Recent advancements in Large Language Models (LLMs) have demonstrated their ability to simulate human-like decision-making, yet the impact of psychological pressures on their decision-making processes remains underexplored. To understand how psychological pressures influence decision-making in LLMs, we tested LLMs on various high-level tasks, using both explicit and implicit pressure prompts. Moreover, we examined LLM responses under different personas to compare with human behavior under pressure. Our findings show that pressures significantly affect LLMs’ decision-making, varying across tasks and models. Persona-based analysis suggests some models exhibit human-like sensitivity to pressure, though with some variability. Furthermore, by analyzing both the responses and reasoning patterns, we identified the values LLMs prioritize under specific social pressures. These insights deepen our understanding of LLM behavior and demonstrate the potential for more realistic social simulation experiments.