The paper introduces QUEST, a method for uncertain knowledge graph completion that adds no trainable parameters to the standard pipeline. QUEST first initializes entity embeddings using the smallest non‑trivial eigenvectors of the confidence‑weighted graph Laplacian, thereby preserving community and hub structure before training. It then applies an unbiased mini‑batch Dirichlet energy regularizer to enforce early‑stage structural consistency, leading to improved confidence and link prediction on most metric‑dataset pairs and eliminating instability spikes on dense graphs.
By Md Abrar Jahin, Taufikur Rahman Fuad, Jay Pujara, Craig A. Knoblock
This study experimentally evaluates large language models (LLMs) for legal decision-making in Austrian and EU value‑added tax (VAT) law. It compares fine‑tuning and retrieval‑augmented generation (RAG) on textbook and real‑world tax consulting cases to identify optimal LLM configurations and assess legal‑reasoning abilities. Results show that properly configured LLMs can aid tax professionals with routine tasks and provide legally grounded justifications, though they are not yet ready for full automation due to challenges like hallucination and handling implicit client knowledge.
By Marina Luketina, Andrea Benkel, Christoph G. Schuetz
The REAP system tackles the AKBC Shared Task 2026, aiming to build knowledge bases from language models without fine‑tuning and within a 32‑B parameter budget. It uses structured chain‑of‑thought reasoning, relation‑specific queries, and a reasoning‑based empty‑set gate to elicit knowledge, then directly extracts it into valid JSON arrays. Evaluated on the test set with the Mistral‑Small‑24B‑Instruct‑2501 model, REAP achieves a macro‑F1 of 0.62, notably high scores on countryLandBordersCountry (0.95), companyTradesAtStockExchange (0.73), and hasArea (0.77).
By Thanh-Dan Bui, Thanh-Trung Do, Tuan-Phong Nguyen
CRAW is a codec‑robust audio watermarking framework designed to embed imperceptible signals into synthetic speech, enabling provenance verification. It improves robustness against neural re‑synthesis, codecs, denoisers, and vocoders while preserving perceptual quality through distortion‑aware training, attention‑based pooling, perceptual masking, and error‑correcting codes. Experiments show CRAW outperforms existing post‑hoc watermarking methods in robustness without compromising audio quality.
The paper discusses the challenges of root cause analysis (RCA) in 5G and 6G telecom networks, where complex cross-layer dependencies make diagnosis difficult. It reviews the progression from rule‑based and machine‑learning RCA methods to emerging large language model (LLM) approaches, highlighting issues such as hallucination and unstable reasoning when using vanilla LLMs. The authors propose a structured reasoning framework that organizes network telemetry into canonical contexts, enforces decision‑path reasoning, and generates evidence‑grounded explanations, showing improved diagnostic accuracy on two 5G RCA datasets.
The paper introduces DKL, a method that decouples knowledge learning from instruction tuning in language models. Instead of fine‑tuning the instruction‑tuned model directly, DKL first extends pre‑training on a base model to embed new knowledge, then merges these weights into the instruction‑tuned model, preserving its instruction‑following abilities. Experiments show DKL raises RAG accuracy from 54.17 % to 79.26 % on retrieval failures, outperforming prior methods while using far less training data.
Loom is a generative consensus framework designed for real‑world root‑cause analysis (RCA) that combines open‑form hypotheses from modular heuristics with a lightweight large language model (LLM). It projects hypotheses into a continuous embedding space and uses an iterative centroid‑based reweighting algorithm to resolve conflicts, producing a single consensus that is then synthesized by one LLM call. On the OpenRCA benchmark, Loom achieves state‑of‑the‑art accuracy on Bank and Market‑2 while being significantly faster and more efficient than existing autonomous agents.
The article discusses the importance of a Retrieval-Augmented Generation (RAG) system providing clear evidence when it states that information is not present in a document. It outlines four distinct types of evidence that should accompany such a claim to avoid presenting a confident but incorrect answer or an unsupported “no answer.” The piece emphasizes that each evidence type serves as a safeguard against misinformation in enterprise document intelligence.
By Kezhan Shi
The paper introduces a multimodal framework that learns subcellularly resolved cell embeddings by integrating RNA expression profiles, protein sequence representations, and protein structural information. It uses a cross‑attention architecture to model interactions across distinct subcellular compartments, producing embeddings that capture both molecular expression patterns and functional protein properties. This approach is presented as the first to jointly incorporate transcriptomic data, protein sequences, and structural knowledge within a unified cross‑modal learning paradigm.
The paper introduces a self-referential retrosynthesis framework for explainable AI provenance forensics that works with fixed generative models. It uses a jointly optimized encoder-decoder pair to embed client inputs, allowing the generator to produce high-fidelity outputs while enabling round-trip consistency checks. The method eliminates the need for watermarking or generator modifications and provides interpretable evidence linking generated images back to their source inputs.
The paper introduces EmoStance, a method for controlling the affective orientation of empathetic responses in dialogue systems. It leverages weak supervision from multi‑annotator emoji distributions to create a latent control space that approximates listener stance, and uses a frozen instruction‑tuned LLM steered by continuous prefix embeddings. Evaluation shows a 62.2% decisive win rate over baselines, especially in contextual specificity and perceived responsiveness.
The paper introduces C$^{3}$T, a Counterfactual Causal Conversation Transformer that models sentiment shifts in social‑media conversation trees by treating discourse moves such as denial, evidence, and toxicity as interventions. It adds a causal sentiment reasoning layer, CaSiRe, to public rumor datasets, providing sentiment, shift, intervention, and causal‑source annotations. Experiments show that C$^{3}$T outperforms text‑only, graph‑based, and temporal baselines in predicting sentiment and attribution, revealing that denials and evidence reduce negativity while toxicity increases it.
The paper introduces EGT-KG, an evidence‑grounded typed knowledge graph retrieval framework designed to enhance scientific question answering with small language models (SLMs). It compares three QA settings—standard Retrieval‑Augmented Generation (RAG) and two EGT‑KG variants (automatically generated and expert‑defined relation schemas)—using a six‑dimensional evaluation on a biopolymer‑bound soil composite literature benchmark. Results show that both EGT‑KG variants outperform vanilla RAG, with the llama3:8b model achieving a final score of 70.37 (+14.67%) and 68.82 (+12.14%) for the AS and ES variants, respectively.
By Muran Yu, Jiechao Gao, Yuandong Pan, Barney H. Miao, Andrew C. Lesh, Kincho H. Law, Jie Wang, Michael D. Lepech
arXiv:2609.01018v1 Announce Type: cross
Abstract: Architecture category. Hybrid method: a physics-based analytical pencil-beam (PB) dose engine followed by a 3-D convolutional residual-correction net...
By Lukas Zimmermann, Hermann Fuchs, Attila Simk\'o, Gerd Heilemann
The paper introduces IT-TextFusion, an iterative text-guided image fusion framework that uses text-conditioned feature interaction across multiple fusion and refinement stages. It incorporates deep cross-attention, multi-scale cross-gate fusion, and stage-specific text-conditioned modulation to enable degradation-aware global semantic conditioning while preserving complementary visible and infrared information. Experiments on benchmark datasets demonstrate improvements in information-preservation and perceptual-quality metrics, with some metric-dependent trade-offs.
By Siyang Liu, Peiyi Zhou, Tianle Jin, Rongrong Bian, Zheke Jin, Mengze Gao
The paper investigates how multimodal large language models (MLLMs) handle conflicting evidence presented in text, image, or both forms. Across 13 MLLMs and two datasets, the authors find that models are not robust to knowledge conflict: they tend to accept contradictory image evidence more readily than contradictory text, and when both modalities conflict the preference is arbitrary, depending on input order, model, and dataset. The instability degrades multimodal retrieval-augmented generation and can be exploited by adversarial attacks, while simple mitigation techniques such as prompting, steering, and direct preference optimization largely fail, with supervised fine‑tuning offering only moderate improvement.
By Jungyeon Lee, Yejin Yoon, Taeuk Kim
The paper introduces Drift‑Aware Sparse Routing (DRS), a method for routing requests in a multi‑model language service while respecting compute, latency, memory, or cost budgets. DRS estimates reward and resource use from a rolling audit window, routes using pessimistic reward and optimistic cost estimates, updates resource shadow prices online, and applies a hard meter before commitment. The authors provide theoretical regret bounds that separate control from statistics, showing how the method adapts to non‑stationary prompt distributions and model changes.
By Cheung Hao Lee, Patrick Wong
The paper introduces Reinforcement Learning Enhanced LLM Agents (RLEA), a multi‑agent framework that automates the modeling of complex Vehicle Routing Problems (VRPs). RLEA employs a lightweight neural Planner trained with Soft Q‑learning to coordinate LLM‑based agents, and incorporates an evolutionary memory module and retrieval‑augmented generation to leverage experience and external solver knowledge. Experiments on 48 VRP variants show that RLEA outperforms the prior state‑of‑the‑art method, achieving a 16.67% higher success rate and significantly reducing runtime errors.
By Yi Chen, Zikang Yu, Jiahai Wang, Jinbiao Chen, Jianpeng Zhou, Zizhen Zhang
H2Table introduces a hierarchical hypergraph representation for complex tables, enabling a hypergraph encoder to capture semantic relationships between headers and cells. The framework uses learnable query vectors to extract structural embeddings for large language models. Experiments on the HiTab dataset show a 22.88% improvement over state‑of‑the‑art baselines on tables with four levels of nesting.
By Jia Ling, Yangfan Wang, Chen Tang, Haoming Tan, Yang Yang, Yi Guan, Jingchi Jiang
The paper introduces AVA, a framework that tests whether general NLP embeddings can differentiate logic-sensitive relational semantics in ontologies and knowledge graphs. AVA uses 171,007 contrastive triplets from 163 ontologies, each containing an ontology statement, a paraphrase, and a hard negative with contradictory meaning. Evaluation of over 25 embedding models shows significant limitations, with the best model achieving only 0.739 triplet accuracy and 0.135 for hard negatives; fine‑tuning helps but does not transfer well to downstream Semantic Web tasks.
By Hamed Babaei Giglou, Jennifer D'Souza, S\"oren Auer