Linguistically Informed Evaluation of Multilingual ASR for African Languages

Word Error Rate (WER) mischaracterizes ASR models' performance for African languages by combining phonological, tone, and other linguistic errors into a single lexical error. By contrast, Feature Error Rate (FER) has recently attracted attention as a viable metric that reveals linguistically meaningful errors in models' performance. In this paper, we evaluate three speech encoders on two African languages by complementing WER with CER, and FER, and add a tone-aware extension (TER). We show that by computing errors on phonological features, FER and TER reveal linguistically-salient error patterns even when word-level accuracy remains low. Our results reveal that models perform better on segmental features, while tones (especially mid and downstep) remain the most challenging features. Results on Yoruba show a striking differential in metrics, with WER=0.788, CER=0.305, and FER=0.151. Similarly for Uneme (an endangered language absent from pretraining data) a model with near-total WER and 0.461 CER achieves the relatively low FER of 0.267. This indicates model error is often attributable to individual phonetic feature errors, which is obscured by all-or-nothing metrics like WER.

When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making

Most adversarial threats in artificial intelligence target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and act on model recommendations. Large Language Models generate fluent natural-language explanations that shape how users perceive and trust AI outputs, revealing a new attack surface at the cognitive layer: the communication channel between AI and its users. We introduce adversarial explanation attacks (AEAs), where an attacker manipulates the framing of LLM-generated explanations to modulate human trust in incorrect outputs. We formalize this behavioral threat through the trust miscalibration gap, a metric that captures the difference in human trust between correct and incorrect outputs under adversarial explanations. By incorporating this gap, AEAs explore the daunting threats in which persuasive explanations reinforce users' trust in incorrect predictions. To characterize this threat, we conducted a controlled experiment (n = 205), systematically varying four dimensions of explanation framing: reasoning mode, evidence type, communication style, and presentation format. Our findings show that users report nearly identical trust for adversarial and benign explanations, with adversarial explanations preserving the vast majority of benign trust despite being incorrect. The most vulnerable cases arise when AEAs closely resemble expert communication, combining authoritative evidence, neutral tone, and domain-appropriate reasoning. Vulnerability is highest on hard tasks, in fact-driven domains, and among participants who are less formally educated, younger, or highly trusting of AI. This is the first systematic security study that treats explanations as an adversarial cognitive channel and quantifies their impact on human trust in AI-assisted decision making.

Equal Access, Unequal Interaction: A Counterfactual Audit of LLM Fairness

Prior work on fairness in large language models (LLMs) has primarily focused on access-level behaviors such as refusals and safety filtering. However, equitable access does not ensure equitable interaction quality once a response is provided. In this paper, we conduct a controlled fairness audit examining how LLMs differ in tone, uncertainty, and linguistic framing across demographic identities after access is granted. Using a counterfactual prompt design, we evaluate GPT-4 and LLaMA-3.1-70B on career advice tasks while varying identity attributes along age, gender, and nationality. We assess access fairness through refusal analysis and measure interaction quality using automated linguistic metrics, including sentiment, politeness, and hedging. Identity-conditioned differences are evaluated using paired statistical tests. Both models exhibit zero refusal rates across all identities, indicating uniform access. Nevertheless, we observe systematic, model-specific disparities in interaction quality: GPT-4 expresses significantly higher hedging toward younger male users, while LLaMA exhibits broader sentiment variation across identity groups. These results show that fairness disparities can persist at the interaction level even when access is equal, motivating evaluation beyond refusal-based audits.

DiscoverLLM: From Executing Intents to Discovering Them

To handle ambiguous and open-ended requests, Large Language Models (LLMs) are increasingly trained to interact with users to surface intents they have not yet expressed (e.g., ask clarification questions). However, users are often ambiguous because they have not yet formed their intents: they must observe and explore outcomes to discover what they want. Simply asking "what kind of tone do you want?" fails when users themselves do not know. We introduce DiscoverLLM, a novel and generalizable framework that trains LLMs to help users form and discover their intents. Central to our approach is a novel user simulator that models cognitive state with a hierarchy of intents that progressively concretize as the model surfaces relevant options -- where the degree of concretization serves as a reward signal that models can be trained to optimize. Resulting models learn to collaborate with users by adaptively diverging (i.e., explore options) when intents are unclear, and converging (i.e., refine and implement) when intents concretize. Across proposed interactive benchmarks in creative writing, technical writing, and SVG drawing, DiscoverLLM achieves over 10% higher task performance while reducing conversation length by up to 40%. In a user study with 75 human participants, DiscoverLLM improved conversation satisfaction and efficiency compared to baselines.

Moonworks Lunara Aesthetic II: An Image Variation Dataset

We introduce Lunara Aesthetic II, a publicly released, ethically sourced image dataset designed to support controlled evaluation and learning of contextual consistency in modern image generation and editing systems. The dataset comprises 2,854 anchor-linked variation pairs derived from original art and photographs created by Moonworks. Each variation pair applies contextual transformations, such as illumination, weather, viewpoint, scene composition, color tone, or mood; while preserving a stable underlying identity. Lunara Aesthetic II operationalizes identity-preserving contextual variation as a supervision signal while also retaining Lunara's signature high aesthetic scores. Results show high identity stability, strong target attribute realization, and a robust aesthetic profile that exceeds large-scale web datasets. Released under the Apache 2.0 license, Lunara Aesthetic II is intended for benchmarking, fine-tuning, and analysis of contextual generalization, identity preservation, and edit robustness in image generation and image-to-image systems with interpretable, relational supervision. The dataset is publicly available at: https://huggingface.co/datasets/moonworks/lunara-aesthetic-image-variations.

A Narrowband Fully-Analog Multi-Antenna Transmitter

This paper proposes a narrowband fully-analog $N$-antenna transmitter that emulates the functionality of a narrowband fully-digital $N$-antenna transmitter. Specifically, in symbol interval $m$, the proposed fully-analog transmitter synthesizes an arbitrary complex excitation vector $\bm x[m]\in\mathbb{C}^N$ with prescribed total power $\|\bm x[m]\|_2^2=P$ from a single coherent RF tone, using only tunable phase-control elements embedded in a passive interferometric programmable network. The programmable network is excited through one input port while the remaining $N - 1$ input ports are impedance matched. In the ideal lossless case, the network transfer is unitary and therefore redistributes RF power among antenna ports without dissipative amplitude control. The synthesis task is posed as a unitary state-preparation problem: program a unitary family so that $\bm V(\bm\varphi)\bm e_1=\bm c$, where $\bm c=\bm x/\sqrt{P}$ and $\|\bm c\|_2=1$. We provide a constructive realization and a closed-form programming rule: a binary magnitude-splitting tree allocates the desired per-antenna magnitudes $|c_n|$ using $N -1$ tunable split ratios, and a per-antenna output phase bank assigns the target phases using $N$ tunable phase shifts. The resulting architecture uses $2N-1$ real tunable degrees of freedom and admits a deterministic $O(N)$ programming procedure with no iterative optimization, enabling symbol-by-symbol updates when the chosen phase-control technology supports the required tuning speed. Using representative COTS components, we model the RF-front-end DC power of the proposed fully-analog transmitter and compare it against an equivalent COTS fully-digital array. For $N\le 16$, the comparison indicates significant RF-front-end power savings for the fully-analog architecture. The results in this paper are intended as a proof-of-concept for a narrowband fully-analog transmitter.

Personality Expression Across Contexts: Linguistic and Behavioral Variation in LLM Agents

Large Language Models (LLMs) can be conditioned with explicit personality prompts, yet their behavioral realization often varies depending on context. This study examines how identical personality prompts lead to distinct linguistic, behavioral, and emotional outcomes across four conversational settings: ice-breaking, negotiation, group decision, and empathy tasks. Results show that contextual cues systematically influence both personality expression and emotional tone, suggesting that the same traits are expressed differently depending on social and affective demands. This raises an important question for LLM-based dialogue agents: whether such variations reflect inconsistency or context-sensitive adaptation akin to human behavior. Viewed through the lens of Whole Trait Theory, these findings highlight that LLMs exhibit context-sensitive rather than fixed personality expression, adapting flexibly to social interaction goals and affective conditions.

Supervised makeup transfer with a curated dataset: Decoupling identity and makeup features for enhanced transformation

Diffusion models have recently shown strong progress in generative tasks, offering a more stable alternative to GAN-based approaches for makeup transfer. Existing methods often suffer from limited datasets, poor disentanglement between identity and makeup features, and weak controllability. To address these issues, we make three contributions. First, we construct a curated high-quality dataset using a train-generate-filter-retrain strategy that combines synthetic, realistic, and filtered samples to improve diversity and fidelity. Second, we design a diffusion-based framework that disentangles identity and makeup features, ensuring facial structure and skin tone are preserved while applying accurate and diverse cosmetic styles. Third, we propose a text-guided mechanism that allows fine-grained and region-specific control, enabling users to modify eyes, lips, or face makeup with natural language prompts. Experiments on benchmarks and real-world scenarios demonstrate improvements in fidelity, identity preservation, and flexibility. Examples of our dataset can be found at: https://makeup-adapter.github.io.

SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Prediction?

We explore the use of large language models (LLMs) for next-utterance prediction in human dialogue. Despite recent advances in LLMs demonstrating their ability to engage in natural conversations with users, we show that even leading models surprisingly struggle to predict a human speaker's next utterance. Instead, humans can readily anticipate forthcoming utterances based on multimodal cues, such as gestures, gaze, and emotional tone, from the context. To systematically examine whether LLMs can reproduce this ability, we propose SayNext-Bench, a benchmark that evaluates LLMs and Multimodal LLMs (MLLMs) on anticipating context-conditioned responses from multimodal cues spanning a variety of real-world scenarios. To support this benchmark, we build SayNext-PC, a novel large-scale dataset containing dialogues with rich multimodal cues. Building on this, we further develop a dual-route prediction MLLM, SayNext-Chat, that incorporates cognitively inspired design to emulate predictive processing in conversation. Experimental results demonstrate that our model outperforms state-of-the-art MLLMs in terms of lexical overlap, semantic similarity, and emotion consistency. Our results prove the feasibility of next-utterance prediction with LLMs from multimodal cues and emphasize the (i) indispensable role of multimodal cues and (ii) actively predictive processing as the foundation of natural human interaction, which is missing in current MLLMs. We hope that this exploration offers a new research entry toward more human-like, context-sensitive AI interaction for human-centered AI. Our benchmark and model can be accessed at https://saynext.github.io/.

Benchmarking Machine Translation on Chinese Social Media Texts

The prevalence of rapidly evolving slang, neologisms, and highly stylized expressions in informal user-generated text, particularly on Chinese social media, poses significant challenges for Machine Translation (MT) benchmarking. Specifically, we identify two primary obstacles: (1) data scarcity, as high-quality parallel data requires bilingual annotators familiar with platform-specific slang, and stylistic cues in both languages; and (2) metric limitations, where traditional evaluators like COMET often fail to capture stylistic fidelity and nonstandard expressions. To bridge these gaps, we introduce CSM-MTBench, a benchmark covering five Chinese-foreign language directions and consisting of two expert-curated subsets: Fun Posts, featuring context-rich, slang- and neologism-heavy content, and Social Snippets, emphasizing concise, emotion- and style- driven expressions. Furthermore, we propose tailored evaluation approaches for each subset: measuring the translation success rate of slang and neologisms in Fun Posts, while assessing tone and style preservation in Social Snippets via a hybrid of embedding-based metrics and LLM-as-a-judge. Experiments on over 20 models reveal substantial variation in how current MT systems handle semantic fidelity and informal, social-media-specific stylistic cues. CSM-MTBench thus serves as a rigorous testbed for advancing MT systems capable of mastering real-world Chinese social media texts.