Short text classification has gained significant attention in the information age due to its prevalence and real-world applications. Recent advancements in graph learning combined with contrastive learning have shown promising results in addressing the challenges of semantic sparsity and limited labeled data in short text classification. However, existing models have certain limitations. They rely on explicit data augmentation techniques to generate contrastive views, resulting in semantic corruption and noise. Additionally, these models only focus on learning the intrinsic consistency between the generated views, neglecting valuable discriminative information from other potential views. To address these issues, we propose a Simple graph contrastive learning framework for Short Text Classification (SimSTC). Our approach involves performing graph learning on multiple text-related component graphs to obtain multi-view text embeddings. Subsequently, we directly apply contrastive learning on these embeddings. Notably, our method eliminates the need for data augmentation operations to generate contrastive views while still leveraging the benefits of multi-view contrastive learning. Despite its simplicity, our model achieves outstanding performance, surpassing large language models on various datasets.

Recent advancements in large language models (LLMs) have shown promise in medical applications such as disease diagnosis and treatment planning. However, most existing medical LLMs struggle with the advanced reasoning required for complex clinical scenarios, such as differential diagnosis or personalized treatment suggestions. We proposed FineMedLM-o1, which leverages high-quality synthetic medical data and long-form reasoning data for Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO), enabling advanced dialogue and deep reasoning capabilities. Additionally, we introduced Test-Time Training (TTT) in the medical domain for the first time, facilitating domain adaptation and ensuring reliable, accurate reasoning. Experimental results demonstrate that FineMedLM-o1 achieves a 23% average performance improvement over prior models on key medical benchmarks. Furthermore, the introduction of TTT provides an additional 14% performance boost, highlighting its effectiveness in enhancing medical reasoning capabilities. To support this process, we also proposed a novel method for synthesizing medical dialogue. Compared to other open-source datasets, our dataset stands out as superior in both quality and complexity. The project and data will be released on GitHub.

Generative artificial intelligence (GenAI) holds great promise as a tool to support personalized learning. Teachers need tools to efficiently and effectively enhance content readability of educational texts so that they are matched to individual students reading levels, while retaining key details. Large Language Models (LLMs) show potential to fill this need, but previous research notes multiple shortcomings in current approaches. In this study, we introduced a generalized approach and metrics for the systematic evaluation of the accuracy and consistency in which LLMs, prompting techniques, and a novel multi-agent architecture to simplify sixty informational reading passages, reducing each from the twelfth grade level down to the eighth, sixth, and fourth grade levels. We calculated the degree to which each LLM and prompting technique accurately achieved the targeted grade level for each passage, percentage change in word count, and consistency in maintaining keywords and key phrases (semantic similarity). One-sample t-tests and multiple regression models revealed significant differences in the best performing LLM and prompt technique for each of the four metrics. Both LLMs and prompting techniques demonstrated variable utility in grade level accuracy and consistency of keywords and key phrases when attempting to level content down to the fourth grade reading level. These results demonstrate the promise of the application of LLMs for efficient and precise automated text simplification, the shortcomings of current models and prompting methods in attaining an ideal balance across various evaluation criteria, and a generalizable method to evaluate future systems.

Understanding how misleading and outright false information enters news ecosystems remains a difficult challenge that requires tracking how narratives spread across thousands of fringe and mainstream news websites. To do this, we introduce a system that utilizes encoder-based large language models and zero-shot stance detection to scalably identify and track news narratives and their attitudes across over 4,000 factually unreliable, mixed-reliability, and factually reliable English-language news websites. Running our system over an 18 month period, we track the spread of 146K news stories. Using network-based interference via the NETINF algorithm, we show that the paths of news narratives and the stances of websites toward particular entities can be used to uncover slanted propaganda networks (e.g., anti-vaccine and anti-Ukraine) and to identify the most influential websites in spreading these attitudes in the broader news ecosystem. We hope that increased visibility into our distributed news ecosystem can help with the reporting and fact-checking of propaganda and disinformation.

Existing Theory of Mind (ToM) benchmarks diverge from real-world scenarios in three aspects: 1) they assess a limited range of mental states such as beliefs, 2) false beliefs are not comprehensively explored, and 3) the diverse personality traits of characters are overlooked. To address these challenges, we introduce ToMATO, a new ToM benchmark formulated as multiple-choice QA over conversations. ToMATO is generated via LLM-LLM conversations featuring information asymmetry. By employing a prompting method that requires role-playing LLMs to verbalize their thoughts before each utterance, we capture both first- and second-order mental states across five categories: belief, intention, desire, emotion, and knowledge. These verbalized thoughts serve as answers to questions designed to assess the mental states of characters within conversations. Furthermore, the information asymmetry introduced by hiding thoughts from others induces the generation of false beliefs about various mental states. Assigning distinct personality traits to LLMs further diversifies both utterances and thoughts. ToMATO consists of 5.4k questions, 753 conversations, and 15 personality trait patterns. Our analysis shows that this dataset construction approach frequently generates false beliefs due to the information asymmetry between role-playing LLMs, and effectively reflects diverse personalities. We evaluate nine LLMs on ToMATO and find that even GPT-4o mini lags behind human performance, especially in understanding false beliefs, and lacks robustness to various personality traits.

Multi-modal document retrieval is designed to identify and retrieve various forms of multi-modal content, such as figures, tables, charts, and layout information from extensive documents. Despite its significance, there is a notable lack of a robust benchmark to effectively evaluate the performance of systems in multi-modal document retrieval. To address this gap, this work introduces a new benchmark, named as MMDocIR, encompassing two distinct tasks: page-level and layout-level retrieval. The former focuses on localizing the most relevant pages within a long document, while the latter targets the detection of specific layouts, offering a more fine-grained granularity than whole-page analysis. A layout can refer to a variety of elements such as textual paragraphs, equations, figures, tables, or charts. The MMDocIR benchmark comprises a rich dataset featuring expertly annotated labels for 1,685 questions and bootstrapped labels for 173,843 questions, making it a pivotal resource for advancing multi-modal document retrieval for both training and evaluation. Through rigorous experiments, we reveal that (i) visual retrievers significantly outperform their text counterparts, (ii) MMDocIR train set can effectively benefit the training process of multi-modal document retrieval and (iii) text retrievers leveraging on VLM-text perform much better than those using OCR-text. These findings underscores the potential advantages of integrating visual elements for multi-modal document retrieval.

Artificial intelligence (AI), including large language models and generative AI, is emerging as a significant force in software development, offering developers powerful tools that span the entire development lifecycle. Although software engineering research has extensively studied AI tools in software development, the specific types of interactions between developers and these AI-powered tools have only recently begun to receive attention. Understanding and improving these interactions has the potential to improve productivity, trust, and efficiency in AI-driven workflows. In this paper, we propose a taxonomy of interaction types between developers and AI tools, identifying eleven distinct interaction types, such as auto-complete code suggestions, command-driven actions, and conversational assistance. Building on this taxonomy, we outline a research agenda focused on optimizing AI interactions, improving developer control, and addressing trust and usability challenges in AI-assisted development. By establishing a structured foundation for studying developer-AI interactions, this paper aims to stimulate research on creating more effective, adaptive AI tools for software development.

Configuration translation is a critical and frequent task in network operations. When a network device is damaged or outdated, administrators need to replace it to maintain service continuity. The replacement devices may originate from different vendors, necessitating configuration translation to ensure seamless network operation. However, translating configurations manually is a labor-intensive and error-prone process. In this paper, we propose an intent-based framework for translating network configuration with Large Language Model (LLM) Agents. The core of our approach is an Intent-based Retrieval Augmented Generation (IRAG) module that systematically splits a configuration file into fragments, extracts intents, and generates accurate translations. We also design a two-stage verification method to validate the syntax and semantics correctness of the translated configurations. We implement and evaluate the proposed method on real-world network configurations. Experimental results show that our method achieves 97.74% syntax correctness, outperforming state-of-the-art methods in translation accuracy.

Large Language Models (LLMs), trained on extensive web-scale corpora, have demonstrated remarkable abilities across diverse tasks, especially as they are scaled up. Nevertheless, even state-of-the-art models struggle in certain cases, sometimes failing at problems solvable by young children, indicating that traditional notions of task complexity are insufficient for explaining LLM capabilities. However, exploring LLM capabilities is complicated by the fact that most widely-used models are also "instruction-tuned" to respond appropriately to prompts. With the goal of disentangling the factors influencing LLM performance, we investigate whether instruction-tuned models possess fundamentally different capabilities from base models that are prompted using in-context examples. Through extensive experiments across various model families, scales and task types, which included instruction tuning 90 different LLMs, we demonstrate that the performance of instruction-tuned models is significantly correlated with the in-context performance of their base counterparts. By clarifying what instruction-tuning contributes, we extend prior research into in-context learning, which suggests that base models use priors from pretraining data to solve tasks. Specifically, we extend this understanding to instruction-tuned models, suggesting that their pretraining data similarly sets a limiting boundary on the tasks they can solve, with the added influence of the instruction-tuning dataset.

Traditional similarity-based schema matching methods are incapable of resolving semantic ambiguities and conflicts in domain-specific complex mapping scenarios due to missing commonsense and domain-specific knowledge. The hallucination problem of large language models (LLMs) also makes it challenging for LLM-based schema matching to address the above issues. Therefore, we propose a Knowledge Graph-based Retrieval-Augmented Generation model for Schema Matching, referred to as the KG-RAG4SM. In particular, KG-RAG4SM introduces novel vector-based, graph traversal-based, and query-based graph retrievals, as well as a hybrid approach and ranking schemes that identify the most relevant subgraphs from external large knowledge graphs (KGs). We showcase that KG-based retrieval-augmented LLMs are capable of generating more accurate results for complex matching cases without any re-training. Our experimental results show that KG-RAG4SM outperforms the LLM-based state-of-the-art (SOTA) methods (e.g., Jellyfish-8B) by 35.89% and 30.50% in terms of precision and F1 score on the MIMIC dataset, respectively; KG-RAG4SM with GPT-4o-mini outperforms the pre-trained language model (PLM)-based SOTA methods (e.g., SMAT) by 69.20% and 21.97% in terms of precision and F1 score on the Synthea dataset, respectively. The results also demonstrate that our approach is more efficient in end-to-end schema matching, and scales to retrieve from large KGs. Our case studies on the dataset from the real-world schema matching scenario exhibit that the hallucination problem of LLMs for schema matching is well mitigated by our solution.