Real-world decision-making often begins with identifying which modality contains the most relevant information for a given query. While recent multimodal models have made impressive progress in processing diverse inputs, it remains unclear whether they can reason contrastively across multiple modalities to select the one that best satisfies a natural language prompt. We argue this capability is foundational, especially in retrieval-augmented and decision-time contexts, where systems must evaluate multiple signals and identify which one conveys the relevant information. To evaluate this skill, we introduce Contra4, a dataset for contrastive cross-modal reasoning across four modalities: image, audio, video, and 3D. Each example presents a natural language question alongside multiple candidate modality instances, and the model must select the one that semantically aligns with the prompt. Contra4 combines human-annotated captions with a mixture-of-models round-trip-consistency filter to ensure high-quality supervision, resulting in 174k training examples and a manually verified test set of 2.3k samples. While task-specific fine-tuning helps improve performance by 56% relative to baseline, state-of-the-art models still achieve only an absolute of 56% accuracy overall and 42% in four-modality settings, underscoring a significant limitation in current multimodal models.

Predicting rare outcomes such as startup success is central to venture capital, demanding models that are both accurate and interpretable. We introduce Random Rule Forest (RRF), a lightweight ensemble method that uses a large language model (LLM) to generate simple YES/NO questions in natural language. Each question functions as a weak learner, and their responses are combined using a threshold-based voting rule to form a strong, interpretable predictor. Applied to a dataset of 9,892 founders, RRF achieves a 6.9x improvement over a random baseline on held-out data; adding expert-crafted questions lifts this to 8x and highlights the value of human-LLM collaboration. Compared with zero- and few-shot baselines across three LLM architectures, RRF attains an F0.5 of 0.121, versus 0.086 for the best baseline (+0.035 absolute, +41% relative). By combining the creativity of LLMs with the rigor of ensemble learning, RRF delivers interpretable, high-precision predictions suitable for decision-making in high-stakes domains.

--From dating to job interviews, making new friends or simply chatting with the cashier at checkout, engaging in small talk is a vital, everyday social skill. For adults with Autism Spectrum Disorder (ASD), small talk can be particularly challenging, yet it is essential for social integration, building relationships, and accessing professional opportunities. In this study, we present our development and evaluation of an in-home autonomous robot system that allows users to practice small talk. Results from the week-long study show that adults with ASD enjoyed the training, made notable progress in initiating conversations and improving eye contact, and viewed the system as a valuable tool for enhancing their conversational skills. Imagine a scene where three coworkers are engaging in small talk at the beginning of their workday. One of them is Alex, who has Autism Spectrum Disorder (ASD), a neu-rodevelopmental condition that often makes it challenging to understand and interpret social cues [2]. Not bad... just trying to power through this Monday. How about you, Alex? A: Monday is okay. Anything exciting happen this weekend? B: Y eah, I finally tried that new restaurant. It was fantas-- A: I watched a movie. C: Glad you liked the restaurant, Ben. It's my kids' favorite spot these days... What movie did you watch, Alex? A: "The Martian." At first glance, this brief example of a typical interaction appears unremarkable. It represents the everyday small talk that occurs regularly in many workplaces. For workers with ASD, however, such apparently "easy" interactions may present a real challenge. In this example, while Alex responds to direct questions, the responses are brief and lack elaboration. Alex's responses provide minimal information rather than actively participating in the flow of the conversation. Additionally, Alex's lack of response to the last prompt may suggest difficulty in extending or sustaining the dialogue. Although workers with ASD are often highly trained and skilled in job-specific tasks, they frequently face challenges with social interactions in the workplace.

High-stakes texts such as patent claims, medical records, and technical reports are structurally complex and demand a high degree of reliability and precision. While large language models (LLMs) have recently been applied to automate their generation in high-stakes domains, reliably evaluating such outputs remains a major challenge. Conventional natural language generation (NLG) metrics are effective for generic documents but fail to capture the structural and legal characteristics essential to evaluating complex high-stakes documents. To address this gap, we propose PatentScore, a multi-dimensional evaluation framework specifically designed for one of the most intricate and rigorous domains, patent claims. PatentScore integrates hierarchical decomposition of claim elements, validation patterns grounded in legal and technical standards, and scoring across structural, semantic, and legal dimensions. In experiments on our dataset which consists of 400 Claim1, PatentScore achieved the highest correlation with expert annotations ($r = 0.819$), significantly outperforming widely used NLG metrics. This work establishes a new standard for evaluating LLM-generated patent claims, providing a solid foundation for research on patent generation and validation.

Generative Large Language Models (LLMs) infer user's demographic information from subtle cues in the conversation -- a phenomenon called implicit personalization. Prior work has shown that such inferences can lead to lower quality responses for users assumed to be from minority groups, even when no demographic information is explicitly provided. In this work, we systematically explore how LLMs respond to stereotypical cues using controlled synthetic conversations, by analyzing the models' latent user representations through both model internals and generated answers to targeted user questions. Our findings reveal that LLMs do infer demographic attributes based on these stereotypical signals, which for a number of groups even persists when the user explicitly identifies with a different demographic group. Finally, we show that this form of stereotype-driven implicit personalization can be effectively mitigated by intervening on the model's internal representations using a trained linear probe to steer them toward the explicitly stated identity. Our results highlight the need for greater transparency and control in how LLMs represent user identity.

Adapting cultural values in Large Language Models (LLMs) presents significant challenges, particularly due to biases and limited training data. Prior work primarily aligns LLMs with different cultural values using World Values Survey (WVS) data. However, it remains unclear whether this approach effectively captures cultural nuances or produces distinct cultural representations for various downstream tasks. In this paper, we systematically investigate WVS-based training for cultural value adaptation and find that relying solely on survey data can homogenize cultural norms and interfere with factual knowledge. To investigate these issues, we augment WVS with encyclopedic and scenario-based cultural narratives from Wikipedia and NormAd. While these narratives may have variable effects on downstream tasks, they consistently improve cultural distinctiveness than survey data alone. Our work highlights the inherent complexity of aligning cultural values with the goal of guiding task-specific behavior. We release our code at https://github.com/faridlazuarda/from-surveys-to-narratives.

The advancement of Large Language Models (LLMs) enables flexible and interpretable automatic evaluations. In the field of machine translation evaluation, utilizing LLMs with translation error annotations based on Multidimensional Quality Metrics (MQM) yields more human-aligned judgments. However, current LLM-based evaluation methods still face challenges in accurately identifying error spans and assessing their severity. In this paper, we propose HiMATE, a Hierarchical Multi-Agent Framework for Machine Translation Evaluation. We argue that existing approaches inadequately exploit the fine-grained structural and semantic information within the MQM hierarchy. To address this, we develop a hierarchical multi-agent system grounded in the MQM error typology, enabling granular evaluation of subtype errors. Two key strategies are incorporated to further mitigate systemic hallucinations within the framework: the utilization of the model's self-reflection capability and the facilitation of agent discussion involving asymmetric information. Empirically, HiMATE outperforms competitive baselines across different datasets in conducting human-aligned evaluations. Further analyses underscore its significant advantage in error span detection and severity assessment, achieving an average F1-score improvement of 89% over the best-performing baseline. We make our code and data publicly available at https://github.com/nlp2ct-shijie/HiMATE.

As Large Language Models (LLMs) are increasingly deployed in sensitive domains such as enterprise and government, ensuring that they adhere to user-defined security policies within context is critical-especially with respect to information non-disclosure. While prior LLM studies have focused on general safety and socially sensitive data, large-scale benchmarks for contextual security preservation against attacks remain lacking. To address this, we introduce a novel large-scale benchmark dataset, CoPriva, evaluating LLM adherence to contextual non-disclosure policies in question answering. Derived from realistic contexts, our dataset includes explicit policies and queries designed as direct and challenging indirect attacks seeking prohibited information. We evaluate 10 LLMs on our benchmark and reveal a significant vulnerability: many models violate user-defined policies and leak sensitive information. This failure is particularly severe against indirect attacks, highlighting a critical gap in current LLM safety alignment for sensitive applications. Our analysis reveals that while models can often identify the correct answer to a query, they struggle to incorporate policy constraints during generation. In contrast, they exhibit a partial ability to revise outputs when explicitly prompted. Our findings underscore the urgent need for more robust methods to guarantee contextual security.

Despite their remarkable progress across diverse domains, Large Language Models (LLMs) consistently fail at simple character-level tasks, such as counting letters in words, due to a fundamental limitation: tokenization. In this work, we frame this limitation as a problem of low mutual information and analyze it in terms of concept emergence. Using a suite of 19 synthetic tasks that isolate character-level reasoning in a controlled setting, we show that such capabilities emerge suddenly and only late in training. We find that percolation-based models of concept emergence explain these patterns, suggesting that learning character composition is not fundamentally different from learning commonsense knowledge. To address this bottleneck, we propose a lightweight architectural modification that significantly improves character-level reasoning while preserving the inductive advantages of subword models. Together, our results bridge low-level perceptual gaps in tokenized LMs and provide a principled framework for understanding and mitigating their structural blind spots. We make our code publicly available.

Recent advances in recommendation with large language models (LLMs) often rely on either commonsense augmentation at the item-category level or implicit intent modeling on existing knowledge graphs. However, such approaches struggle to capture grounded user intents and to handle sparsity and cold-start scenarios. In this work, we present LLM-based Intent Knowledge Graph Recommender (IKGR), a novel framework that constructs an intent-centric knowledge graph where both users and items are explicitly linked to intent nodes extracted by a tuning-free, RAG-guided LLM pipeline. By grounding intents in external knowledge sources and user profiles, IKGR canonically represents what a user seeks and what an item satisfies as first-class entities. To alleviate sparsity, we further introduce a mutual-intent connectivity densification strategy, which shortens semantic paths between users and long-tail items without requiring cross-graph fusion. Finally, a lightweight GNN layer is employed on top of the intent-enhanced graph to produce recommendation signals with low latency. Extensive experiments on public and enterprise datasets demonstrate that IKGR consistently outperforms strong baselines, particularly on cold-start and long-tail slices, while remaining efficient through a fully offline LLM pipeline.