In knowledge distillation, a primary focus has been on transforming and balancing multiple distillation components. In this work, we emphasize the importance of thoroughly examining each distillation component, as we observe that not all elements are equally crucial. From this perspective,we decouple the Kullback-Leibler (KL) divergence into three unique elements: Binary Classification Divergence (BCD), Strong Correlation Divergence (SCD), and Weak Correlation Divergence (WCD). Each of these elements presents varying degrees of influence. Leveraging these insights, we present the Correlation-Aware Knowledge Distillation (CAKD) framework. CAKD is designed to prioritize the facets of the distillation components that have the most substantial influence on predictions, thereby optimizing knowledge transfer from teacher to student models. Our experiments demonstrate that adjusting the effect of each element enhances the effectiveness of knowledge transformation. Furthermore, evidence shows that our novel CAKD framework consistently outperforms the baseline across diverse models and datasets. Our work further highlights the importance and effectiveness of closely examining the impact of different parts of distillation process.

Conditioning diffusion and flow models have proven effective for super-resolving small-scale details in natural images. However, in physical sciences such as weather, super-resolving small-scale details poses significant challenges due to: (i) misalignment between input and output distributions (i.e., solutions to distinct partial differential equations (PDEs) follow different trajectories), (ii) multi-scale dynamics, deterministic dynamics at large scales vs. stochastic at small scales, and (iii) limited data, increasing the risk of overfitting. To address these challenges, we propose encoding the inputs to a latent base distribution that is closer to the target distribution, followed by flow matching to generate small-scale physics. The encoder captures the deterministic components, while flow matching adds stochastic small-scale details. To account for uncertainty in the deterministic part, we inject noise into the encoder's output using an adaptive noise scaling mechanism, which is dynamically adjusted based on maximum-likelihood estimates of the encoder's predictions. We conduct extensive experiments on both the realworld CWA weather dataset and the PDE-based Kolmogorov dataset, with the CWA task involving super-resolving the weather variables for the region of Taiwan from 25 km to 2 km scales. Our results show that the proposed stochastic flow matching (SFM) framework significantly outperforms existing methods such as conditional diffusion and flows. Resolving small-scale physics is crucial in many scientific applications (Wilby et al., 1998; Rampal et al., 2022; 2024). For instance, in the atmospheric sciences, accurately capturing small-scale dynamics is essential for local planning and disaster mitigation. The success of conditional diffusion models in super-resolving natural images and videos (Song et al., 2021; Batzolis et al., 2021; Hoogeboom et al., 2023) has recently been extended to super-resolving small-scale physics (Aich et al., 2024; Ling et al., 2024). However, this task faces significant challenges: (C1) Input and target data are often spatially misaligned due to differing PDE solutions operating at various resolutions, leading to divergent trajectories. Additionally, the input and target variables (channels) often represent different physical quantities, causing further misalignment. Few efforts have been made to directly address these challenges in generative learning. Prior work typically relies on residual learning approaches (Mardani et al., 2023; Zhao et al., 2021).

To manipulate objects or dance together, humans and robots exchange energy and haptic information. While the exchange of energy in human-robot interaction has been extensively investigated, the underlying exchange of haptic information is not well understood. Here, we develop a computational model of the mechanical and sensory interactions between agents that can tune their viscoelasticity while considering their sensory and motor noise. The resulting stochastic-optimal-information-and-effort (SOIE) controller predicts how the exchange of haptic information and the performance can be improved by adjusting viscoelasticity. This controller was first implemented on a robot-robot experiment with a tracking task which showed its superior performance when compared to either stiff or compliant control. Importantly, the optimal controller also predicts how connected humans alter their muscle activation to improve haptic communication, with differentiated viscoelasticity adjustment to their own sensing noise and haptic perturbations. A human-robot experiment then illustrated the applicability of this optimal control strategy for robots, yielding improved tracking performance and effective haptic communication as the robot adjusted its viscoelasticity according to its own and the user's noise characteristics. The proposed SOIE controller may thus be used to improve haptic communication and collaboration of humans and robots.

Summarization is one of the most common tasks performed by large language models (LLMs), especially in applications like Retrieval-Augmented Generation (RAG). However, existing evaluations of hallucinations in LLM-generated summaries, and evaluations of hallucination detection models both suffer from a lack of diversity and recency in the LLM and LLM families considered. This paper introduces FaithBench, a summarization hallucination benchmark comprising challenging hallucinations made by 10 modern LLMs from 8 different families, with ground truth annotations by human experts. ``Challenging'' here means summaries on which popular, state-of-the-art hallucination detection models, including GPT-4o-as-a-judge, disagreed on. Our results show GPT-4o and GPT-3.5-Turbo produce the least hallucinations. However, even the best hallucination detection models have near 50\% accuracies on FaithBench, indicating lots of room for future improvement. The repo is https://github.com/vectara/FaithBench

Fuzzy Neural Networks (FNNs) are effective machine learning models for classification tasks, commonly based on the Takagi-Sugeno-Kang (TSK) fuzzy system. However, when faced with high-dimensional data, especially with noise, FNNs encounter challenges such as vanishing gradients, excessive fuzzy rules, and limited access to prior knowledge. To address these challenges, we propose a novel fuzzy system, the Self-Constructing Multi-Expert Fuzzy System (SOME-FS). It combines two learning strategies: mixed structure learning and multi-expert advanced learning. The former enables each base classifier to effectively determine its structure without requiring prior knowledge, while the latter tackles the issue of vanishing gradients by enabling each rule to focus on its local region, thereby enhancing the robustness of the fuzzy classifiers. The overall ensemble architecture enhances the stability and prediction performance of the fuzzy system. Our experimental results demonstrate that the proposed SOME-FS is effective in high-dimensional tabular data, especially in dealing with uncertainty. Moreover, our stable rule mining process can identify concise and core rules learned by the SOME-FS.

The success of large language models (LLMs) has prompted efforts to integrate speech and audio data, aiming to create general foundation models capable of processing both textual and non-textual inputs. Recent advances, such as GPT-4o, highlight the potential for end-to-end speech LLMs, which preserves non-semantic information and world knowledge for deeper speech understanding. To guide the development of speech LLMs, we propose a five-level roadmap, ranging from basic automatic speech recognition (ASR) to advanced superhuman models capable of integrating non-semantic information with abstract acoustic knowledge for complex tasks. Moreover, we design a benchmark, SAGI Bechmark, that standardizes critical aspects across various tasks in these five levels, uncovering challenges in using abstract acoustic knowledge and completeness of capability. Our findings reveal gaps in handling paralinguistic cues and abstract acoustic knowledge, and we offer future directions. This paper outlines a roadmap for advancing speech LLMs, introduces a benchmark for evaluation, and provides key insights into their current limitations and potential.

Deriving inference from heterogeneous inputs (such as images, text, and audio) is an important skill for humans to perform day-to-day tasks. A similar ability is desirable for the development of advanced Artificial Intelligence (AI) systems. While state-of-the-art models are rapidly closing the gap with human-level performance on diverse computer vision and NLP tasks separately, they struggle to solve tasks that require joint reasoning over visual and textual modalities. Inspired by GLUE (Wang et. al., 2018)- a multitask benchmark for natural language understanding, we propose VL-GLUE in this paper. VL-GLUE consists of over 100k samples spanned across seven different tasks, which at their core require visuo-linguistic reasoning. Moreover, our benchmark comprises of diverse image types (from synthetically rendered figures, and day-to-day scenes to charts and complex diagrams) and includes a broad variety of domain-specific text (from cooking, politics, and sports to high-school curricula), demonstrating the need for multi-modal understanding in the real-world. We show that this benchmark is quite challenging for existing large-scale vision-language models and encourage development of systems that possess robust visuo-linguistic reasoning capabilities.

We investigate and observe the behaviour and performance of Large Language Model (LLM)-backed chatbots in addressing misinformed prompts and questions with demographic information within the domains of Climate Change and Mental Health. Through a combination of quantitative and qualitative methods, we assess the chatbots' ability to discern the veracity of statements, their adherence to facts, and the presence of bias or misinformation in their responses. Our quantitative analysis using True/False questions reveals that these chatbots can be relied on to give the right answers to these close-ended questions. However, the qualitative insights, gathered from domain experts, shows that there are still concerns regarding privacy, ethical implications, and the necessity for chatbots to direct users to professional services. We conclude that while these chatbots hold significant promise, their deployment in sensitive areas necessitates careful consideration, ethical oversight, and rigorous refinement to ensure they serve as a beneficial augmentation to human expertise rather than an autonomous solution.

Large language models (LLMs) must often respond to highly ambiguous user requests. In such cases, the LLM's best response may be to ask a clarifying question to elicit more information. We observe existing LLMs often respond by presupposing a single interpretation of such ambiguous requests, frustrating users who intended a different interpretation. We speculate this is caused by current preference data labeling practice, where LLM responses are evaluated only on their prior contexts. To address this, we propose to assign preference labels by simulating their expected outcomes in the future turns. This allows LLMs to learn to ask clarifying questions when it can generate responses that are tailored to each user interpretation in future turns. In experiments on open-domain QA, we compare systems that trained using our proposed preference labeling methods against standard methods, which assign preferences based on only prior context. We evaluate systems based on their ability to ask clarifying questions that can recover each user's interpretation and expected answer, and find that our training with our proposed method trains LLMs to ask clarifying questions with a 5% improvement in F1 measured against the answer set from different interpretations of each query. Ambiguity is a hallmark of natural language that enables concise communication by allowing speakers to exclude details that are inferable from the context (e.g., conversational, temporal, geographical) (Piantadosi et al., 2012). At times, however, the speaker's intent is unclear despite the context, and further interaction is necessary to clarify their intent. Asking clarifying questions is particularly important for large language models (LLMs), which are tasked with serving a wide audience, often without access to the personalized context available in human interactions. In this work, we develop LLMs that can ask clarifying questions to resolve ambiguity in their users' requests. State-of-the-art LLMs (OpenAI, 2023; Gemini Team, 2024) often do not ask clarifying questions when presented with an ambiguous request, and instead respond directly by assuming the user's intent (see an example in Figure 1).

Natural Language Processing (NLP) is a vital computational method for addressing language processing, analysis, and generation. NLP tasks form the core of many daily applications, from automatic text correction to speech recognition. While significant research has focused on NLP tasks for the English language, less attention has been given to Modern Standard Arabic and Dialectal Arabic. Globalization has also contributed to the rise of Code-Switching (CS), where speakers mix languages within conversations and even within individual words (intra-word CS). This is especially common in Arab countries, where people often switch between dialects or between dialects and a foreign language they master. CS between Arabic and English is frequent in Egypt, especially on social media. Consequently, a significant amount of code-switched content can be found online. Such code-switched data needs to be investigated and analyzed for several NLP tasks to tackle the challenges of this multilingual phenomenon and Arabic language challenges. No work has been done before for several integral NLP tasks on Arabic-English CS data. In this work, we focus on the Named Entity Recognition (NER) task and other tasks that help propose a solution for the NER task on CS data, e.g., Language Identification. This work addresses this gap by proposing and applying state-of-the-art techniques for Modern Standard Arabic and Arabic-English NER. We have created the first annotated CS Arabic-English corpus for the NER task. Also, we apply two enhancement techniques to improve the NER tagger on CS data using CS contextual embeddings and data augmentation techniques. All methods showed improvements in the performance of the NER taggers on CS data. Finally, we propose several intra-word language identification approaches to determine the language type of a mixed text and identify whether it is a named entity or not.