Vision-Language Models (VLMs) are essential for multimodal tasks, especially compositional reasoning (CR) tasks, which require distinguishing fine-grained semantic differences between visual and textual embeddings. However, existing methods primarily fine-tune the model by generating text-based hard negative samples, neglecting the importance of image-based negative samples, which results in insufficient training of the visual encoder and ultimately impacts the overall performance of the model. Moreover, negative samples are typically treated uniformly, without considering their difficulty levels, and the alignment of positive samples is insufficient, which leads to challenges in aligning difficult sample pairs. To address these issues, we propose Adaptive Hard Negative Perturbation Learning (AHNPL). AHNPL translates text-based hard negatives into the visual domain to generate semantically disturbed image-based negatives for training the model, thereby enhancing its overall performance. AHNPL also introduces a contrastive learning approach using a multimodal hard negative loss to improve the model's discrimination of hard negatives within each modality and a dynamic margin loss that adjusts the contrastive margin according to sample difficulty to enhance the distinction of challenging sample pairs. Experiments on three public datasets demonstrate that our method effectively boosts VLMs' performance on complex CR tasks. The source code is available at https://github.com/nynu-BDAI/AHNPL.

Large language models have become multimodal, and many of them are said to integrate their modalities using common representations. If this were true, a drawing of a car as an image, for instance, should map to a similar area in the latent space as a textual description of the strokes that form the drawing. To explore this in a black-box access regime to these models, we propose the use of machine teaching, a theory that studies the minimal set of examples a teacher needs to choose so that the learner captures the concept. In this paper, we evaluate the complexity of teaching vision-language models a subset of objects in the Quick, Draw! dataset using two presentations: raw images as bitmaps and trace coordinates in TikZ format. The results indicate that image-based representations generally require fewer segments and achieve higher accuracy than coordinate-based representations. But, surprisingly, the teaching size usually ranks concepts similarly across both modalities, even when controlling for (a human proxy of) concept priors, suggesting that the simplicity of concepts may be an inherent property that transcends modality representations.

As multi-turn dialogues with large language models (LLMs) grow longer and more complex, how can users better evaluate and review progress on their conversational goals? We present OnGoal, an LLM chat interface that helps users better manage goal progress. OnGoal provides real-time feedback on goal alignment through LLM-assisted evaluation, explanations for evaluation results with examples, and overviews of goal progression over time, enabling users to navigate complex dialogues more effectively. Through a study with 20 participants on a writing task, we evaluate OnGoal against a baseline chat interface without goal tracking. Using OnGoal, participants spent less time and effort to achieve their goals while exploring new prompting strategies to overcome miscommunication, suggesting tracking and visualizing goals can enhance engagement and resilience in LLM dialogues. Our findings inspired design implications for future LLM chat interfaces that improve goal communication, reduce cognitive load, enhance interactivity, and enable feedback to improve LLM performance.

Retrieval-Augmented Generation (RAG) has emerged as a powerful solution to mitigate the limitations of Large Language Models (LLMs), such as hallucinations and outdated knowledge. However, deploying RAG-based tools in Small and Medium Enterprises (SMEs) remains a challenge due to their limited resources and lack of expertise in natural language processing (NLP). This paper introduces EASI-RAG, Enterprise Application Support for Industrial RAG, a structured, agile method designed to facilitate the deployment of RAG systems in industrial SME contexts. EASI-RAG is based on method engineering principles and comprises well-defined roles, activities, and techniques. The method was validated through a real-world case study in an environmental testing laboratory, where a RAG tool was implemented to answer operators queries using data extracted from operational procedures. The system was deployed in under a month by a team with no prior RAG experience and was later iteratively improved based on user feedback. Results demonstrate that EASI-RAG supports fast implementation, high user adoption, delivers accurate answers, and enhances the reliability of underlying data. This work highlights the potential of RAG deployment in industrial SMEs. Future works include the need for generalization across diverse use cases and further integration with fine-tuned models.

In this paper, we introduce InSQuAD, designed to enhance the performance of In-Context Learning (ICL) models through Submodular Mutual Information} (SMI) enforcing Quality and Diversity among in-context exemplars. InSQuAD achieves this through two principal strategies: First, we model the ICL task as a targeted selection problem and introduce a unified selection strategy based on SMIs which mines relevant yet diverse in-context examples encapsulating the notions of quality and diversity. Secondly, we address a common pitfall in existing retrieval models which model query relevance, often overlooking diversity, critical for ICL. InSQuAD introduces a combinatorial training paradigm which learns the parameters of an SMI function to enforce both quality and diversity in the retrieval model through a novel likelihood-based loss. To further aid the learning process we augment an existing multi-hop question answering dataset with synthetically generated paraphrases. Adopting the retrieval model trained using this strategy alongside the novel targeted selection formulation for ICL on nine benchmark datasets shows significant improvements validating the efficacy of our approach.

Large audio language models (LALMs) extend language understanding into the auditory domain, yet their ability to perform low-level listening, such as pitch and duration detection, remains underexplored. However, low-level listening is critical for real-world, out-of-distribution tasks where models must reason about unfamiliar sounds based on fine-grained acoustic cues. To address this gap, we introduce the World-of-Whale benchmark (WoW-Bench) to evaluate low-level auditory perception and cognition using marine mammal vocalizations. WoW-bench is composed of a Perception benchmark for categorizing novel sounds and a Cognition benchmark, inspired by Bloom's taxonomy, to assess the abilities to remember, understand, apply, and analyze sound events. For the Cognition benchmark, we additionally introduce distractor questions to evaluate whether models are truly solving problems through listening rather than relying on other heuristics. Experiments with state-of-the-art LALMs show performance far below human levels, indicating a need for stronger auditory grounding in LALMs.

Proactive dialogue has emerged as a critical and challenging research problem in advancing large language models (LLMs). Existing works predominantly focus on domain-specific or task-oriented scenarios, which leads to fragmented evaluations and limits the comprehensive exploration of models' proactive conversation abilities. In this work, we propose ProactiveEval, a unified framework designed for evaluating proactive dialogue capabilities of LLMs. This framework decomposes proactive dialogue into target planning and dialogue guidance, establishing evaluation metrics across various domains. Moreover, it also enables the automatic generation of diverse and challenging evaluation data. Based on the proposed framework, we develop 328 evaluation environments spanning 6 distinct domains. Through experiments with 22 different types of LLMs, we show that DeepSeek-R1 and Claude-3.7-Sonnet exhibit exceptional performance on target planning and dialogue guidance tasks, respectively. Finally, we investigate how reasoning capabilities influence proactive behaviors and discuss their implications for future model development.

In-Context Learning (ICL) has become a powerful paradigm that enables LLMs to perform a wide range of tasks without task-specific fine-tuning. However, the effectiveness of ICL heavily depends on the quality of exemplar selection. In particular, for structured prediction tasks such as semantic parsing, existing ICL selection strategies often overlook structural alignment, leading to suboptimal performance and poor generalization. To address this issue, we propose a novel two-stage exemplar selection strategy that achieves a strong balance between efficiency, generalizability, and performance. First, we fine-tune a BERT-based retriever using structure-aware supervision, guiding it to select exemplars that are both semantically relevant and structurally aligned. Then, we enhance the retriever with a plug-in module, which amplifies syntactically meaningful information in the hidden representations. This plug-in is model-agnostic, requires minimal overhead, and can be seamlessly integrated into existing pipelines. Experiments on four benchmarks spanning three semantic parsing tasks demonstrate that our method consistently outperforms existing baselines with multiple recent LLMs as inference-time models.

Large language models (LLMs) have become essential for applications such as text summarization, sentiment analysis, and automated question-answering. Recently, LLMs have also been integrated into relational database management systems to enhance querying and support advanced data processing. Companies such as Amazon, Databricks, Google, and Snowflake offer LLM invocation directly within SQL, denoted as LLM queries, to boost data insights. However, open-source solutions currently have limited functionality and poor performance. In this work, we present an early exploration of two open-source systems and one enterprise platform, using five representative queries to expose functional, performance, and scalability limits in today's SQL-invoked LLM integrations. We identify three main issues: enforcing structured outputs, optimizing resource utilization, and improving query planning. We implemented initial solutions and observed improvements in accommodating LLM powered SQL queries. These early gains demonstrate that tighter integration of LLM+DBMS is the key to scalable and efficient processing of LLM queries.

Qiskit is an open-source quantum computing framework that allows users to design, simulate, and run quantum circuits on real quantum hardware. We explore post-training techniques for LLMs to assist in writing Qiskit code. We introduce quantum verification as an effective method for ensuring code quality and executability on quantum hardware. To support this, we developed a synthetic data pipeline that generates quantum problem-unit test pairs and used it to create preference data for aligning LLMs with DPO. Additionally, we trained models using GRPO, leveraging quantum-verifiable rewards provided by the quantum hardware. Our best-performing model, combining DPO and GRPO, surpasses the strongest open-source baselines on the challenging Qiskit-HumanEval-hard benchmark.