Biological knowledge bases provide systemically functional pathways of cells or organisms in terms of molecular interaction. However, recognizing more targeted pathways, particularly when incorporating wet-lab experimental data, remains challenging and typically requires downstream biological analyses and expertise. In this paper, we frame this challenge as a solvable graph learning and explaining task and propose a novel pathway inference framework, ExPath, that explicitly integrates experimental data, specifically amino acid sequences (AA-seqs), to classify various graphs (bio-networks) in biological databases. The links (representing pathways) that contribute more to classification can be considered as targeted pathways. Technically, ExPath comprises three components: (1) a large protein language model (pLM) that encodes and embeds AA-seqs into graph, overcoming traditional obstacles in processing AA-seq data, such as BLAST; (2) PathMamba, a hybrid architecture combining graph neural networks (GNNs) with state-space sequence modeling (Mamba) to capture both local interactions and global pathway-level dependencies; and (3) PathExplainer, a subgraph learning module that identifies functionally critical nodes and edges through trainable pathway masks. We also propose ML-oriented biological evaluations and a new metric. The experiments involving 301 bio-networks evaluations demonstrate that pathways inferred by ExPath maintain biological meaningfulness. We will publicly release curated 301 bio-network data soon.

Continuous Integration (CI) is a cornerstone of modern software development. However, while widely adopted in traditional software projects, applying CI practices to Machine Learning (ML) projects presents distinctive characteristics. For example, our previous work revealed that ML projects often experience longer build durations and lower test coverage rates compared to their non-ML counterparts. Building on these quantitative findings, this study surveys 155 practitioners from 47 ML projects to investigate the underlying reasons for these distinctive characteristics through a qualitative perspective. Practitioners highlighted eight key differences, including test complexity, infrastructure requirements, and build duration and stability. Common challenges mentioned by practitioners include higher project complexity, model training demands, extensive data handling, increased computational resource needs, and dependency management, all contributing to extended build durations. Furthermore, ML systems' non-deterministic nature, data dependencies, and computational constraints were identified as significant barriers to effective testing. The key takeaway from this study is that while foundational CI principles remain valuable, ML projects require tailored approaches to address their unique challenges. To bridge this gap, we propose a set of ML-specific CI practices, including tracking model performance metrics and prioritizing test execution within CI pipelines. Additionally, our findings highlight the importance of fostering interdisciplinary collaboration to strengthen the testing culture in ML projects. By bridging quantitative findings with practitioners' insights, this study provides a deeper understanding of the interplay between CI practices and the unique demands of ML projects, laying the groundwork for more efficient and robust CI strategies in this domain.

The Four-Element Theory is a fundamental framework in criminal law, defining the constitution of crime through four dimensions: Subject, Object, Subjective aspect, and Objective aspect. This theory is widely referenced in legal reasoning, and many Large Language Models (LLMs) attempt to incorporate it when handling legal tasks. However, current approaches rely on LLMs' internal knowledge to incorporate this theory, often lacking completeness and representativeness. To address this limitation, we introduce JUREX-4E, an expert-annotated knowledge base covering 155 criminal charges. It is structured through a progressive hierarchical annotation framework that prioritizes legal source validity and employs diverse legal interpretation methods to ensure comprehensiveness and authority. We evaluate JUREX-4E on the Similar Charge Distinction task and apply it to Legal Case Retrieval, demonstrating its effectiveness in improving LLM performance. Experimental results validate the high quality of JUREX-4E and its substantial impact on downstream legal tasks, underscoring its potential for advancing legal AI applications. Code: https://github.com/THUlawtech/JUREX

The increasing complexity and scale of modern telecommunications networks demand intelligent automation to enhance efficiency, adaptability, and resilience. Agentic AI has emerged as a key paradigm for intelligent communications and networking, enabling AI-driven agents to perceive, reason, decide, and act within dynamic networking environments. However, effective decision-making in telecom applications, such as network planning, management, and resource allocation, requires integrating retrieval mechanisms that support multi-hop reasoning, historical cross-referencing, and compliance with evolving 3GPP standards. This article presents a forward-looking perspective on generative information retrieval-inspired intelligent communications and networking, emphasizing the role of knowledge acquisition, processing, and retrieval in agentic AI for telecom systems. We first provide a comprehensive review of generative information retrieval strategies, including traditional retrieval, hybrid retrieval, semantic retrieval, knowledge-based retrieval, and agentic contextual retrieval. We then analyze their advantages, limitations, and suitability for various networking scenarios. Next, we present a survey about their applications in communications and networking. Additionally, we introduce an agentic contextual retrieval framework to enhance telecom-specific planning by integrating multi-source retrieval, structured reasoning, and self-reflective validation. Experimental results demonstrate that our framework significantly improves answer accuracy, explanation consistency, and retrieval efficiency compared to traditional and semantic retrieval methods. Finally, we outline future research directions.

Large language models (LLMs) have demonstrated impressive capabilities in disease diagnosis. However, their effectiveness in identifying rarer diseases, which are inherently more challenging to diagnose, remains an open question. Rare disease performance is critical with the increasing use of LLMs in healthcare settings. This is especially true if a primary care physician needs to make a rarer prognosis from only a patient conversation so that they can take the appropriate next step. To that end, several clinical decision support systems are designed to support providers in rare disease identification. Yet their utility is limited due to their lack of knowledge of common disorders and difficulty of use. In this paper, we propose RareScale to combine the knowledge LLMs with expert systems. We use jointly use an expert system and LLM to simulate rare disease chats. This data is used to train a rare disease candidate predictor model. Candidates from this smaller model are then used as additional inputs to black-box LLM to make the final differential diagnosis. Thus, RareScale allows for a balance between rare and common diagnoses. We present results on over 575 rare diseases, beginning with Abdominal Actinomycosis and ending with Wilson's Disease. Our approach significantly improves the baseline performance of black-box LLMs by over 17% in Top-5 accuracy. We also find that our candidate generation performance is high (e.g. 88.8% on gpt-4o generated chats).

Empirical human-AI alignment aims to make AI systems act in line with observed human behavior. While noble in its goals, we argue that empirical alignment can inadvertently introduce statistical biases that warrant caution. This position paper thus advocates against naive empirical alignment, offering prescriptive alignment and a posteriori empirical alignment as alternatives. We substantiate our principled argument by tangible examples like human-centric decoding of language models.

While language technologies have advanced significantly, current approaches fail to address the complex sociocultural dimensions of linguistic preservation. AI Thinking proposes a meaning-centered framework that would transform technological development from creating tools FOR communities to co-creating solutions WITH them. This approach recognizes that meaningful solutions emerge through the interplay of cultural understanding, community agency, and technological innovation. The proposal articulates a holistic methodology and a five-layer technological ecosystem where communities maintain control over their linguistic and cultural knowledge representation. This systematic integration of community needs, cultural preservation, and advanced capabilities could revolutionize how we approach linguistic diversity preservation in the digital age.

In real-world information-seeking scenarios, users have dynamic and diverse needs, requiring RAG systems to demonstrate adaptable resilience. To comprehensively evaluate the resilience of current RAG methods, we introduce HawkBench, a human-labeled, multi-domain benchmark designed to rigorously assess RAG performance across categorized task types. By stratifying tasks based on information-seeking behaviors, HawkBench provides a systematic evaluation of how well RAG systems adapt to diverse user needs. Unlike existing benchmarks, which focus primarily on specific task types (mostly factoid queries) and rely on varying knowledge bases, HawkBench offers: (1) systematic task stratification to cover a broad range of query types, including both factoid and rationale queries, (2) integration of multi-domain corpora across all task types to mitigate corpus bias, and (3) rigorous annotation for high-quality evaluation. HawkBench includes 1,600 high-quality test samples, evenly distributed across domains and task types. Using this benchmark, we evaluate representative RAG methods, analyzing their performance in terms of answer quality and response latency. Our findings highlight the need for dynamic task strategies that integrate decision-making, query interpretation, and global knowledge understanding to improve RAG generalizability. We believe HawkBench serves as a pivotal benchmark for advancing the resilience of RAG methods and their ability to achieve general-purpose information seeking.

Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, but they remain susceptible to hallucination, particularly object hallucination where non-existent objects or incorrect attributes are fabricated in generated descriptions. Existing detection methods achieve strong performance but rely heavily on expensive API calls and iterative LVLM-based validation, making them impractical for large-scale or offline use. To address these limitations, we propose CutPaste\&Find, a lightweight and training-free framework for detecting hallucinations in LVLM-generated outputs. Our approach leverages off-the-shelf visual and linguistic modules to perform multi-step verification efficiently without requiring LVLM inference. At the core of our framework is a Visual-aid Knowledge Base that encodes rich entity-attribute relationships and associated image representations. We introduce a scaling factor to refine similarity scores, mitigating the issue of suboptimal alignment values even for ground-truth image-text pairs. Comprehensive evaluations on benchmark datasets, including POPE and R-Bench, demonstrate that CutPaste\&Find achieves competitive hallucination detection performance while being significantly more efficient and cost-effective than previous methods.

Knowledge base question answering (KBQA) aims to answer user questions in natural language using rich human knowledge stored in large KBs. As current KBQA methods struggle with unseen knowledge base elements at test time,we introduce SG-KBQA: a novel model that injects schema contexts into entity retrieval and logical form generation to tackle this issue. It uses the richer semantics and awareness of the knowledge base structure provided by schema contexts to enhance generalizability. We show that SG-KBQA achieves strong generalizability, outperforming state-of-the-art models on two commonly used benchmark datasets across a variety of test settings. Code will be released upon paper publication.