Semantic Web and Ontologies

Neueste Paper

• CypherTurn: A Multi-Turn Benchmark for Conversational Text-to-Cypher Evaluation and the Autonomy Divergence

  Yuzhe Zhang, Weijie Zhu, Haolin Yang, Ziyun Zhang, Xianwei Xue, Mengke Chen, Qiutong Pan, Huaqian Cai · 1. Oktober 2026

  Graph databases are increasingly queried through natural language, yet every existing benchmark evaluates isolated single-turn queries rather than the multi-turn sessions through which analysts actually work. We introduce CypherTurn, the first benchmark for conversational Text-to-Cypher evaluation, …

• The Canonical Order Problem: When Large Language Models Are Unreliable Knowledge Bases for Multi-Valued Relations

  Timo Pierre Schrader, Annemarie Friedrich, Simon Razniewski, Lukas Lange · 1. Oktober 2026

  Large language models (LLMs) are increasingly used as knowledge bases (KBs) due to the vast amount of knowledge they acquire during pre-training. While many works focus on extracting single relational triples, most real-world relations are multi-valued and require generating sets of entities. In t…

• On the (In)effectiveness of AMR Augmentation for Large Language Models

  Hoa Quynh Nhung Nguyen, Jacopo Staiano, Michael Sullivan · 1. Oktober 2026

  While Abstract Meaning Representation (AMR) has historically improved performance on a range of NLP tasks, the benefit---or lack thereof---of AMR augmentation for modern LLMs is thus far unclear. In this paper, we attempt to reproduce recent work that reported substantial downstream gains from AMR a…

• What Limits Recursive Reasoning Models: Optimization, Architecture and Test-Time Scaling

  Yuliana Shakhvalieva, Dmitrii Kharchev, Viacheslav Bezrukov, Inessa Fedorova, Dmitry Bocharov, Ivan Oseledets, Valerii Ternovskii · 1. Oktober 2026

  Recursive reasoning models apply a small shared Transformer block many times to refine a latent state. This gives them large effective depth with few parameters and makes them strong on algorithmic tasks. Such compact solvers are natural candidates for tools that an LLM can call on narrow algorithmi…

• Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment

  Yihuai Hong, Shauli Ravfogel, Chen Zhao, Eunsol Choi · 1. Oktober 2026

  Chain-of-thought (CoT) traces often serve as a proxy for how Large Language Models (LLMs) arrive at their answers. However, growing evidence shows that models' CoT often fails to reflect their internal computations and can be changed without affecting their final answers. In this work, we measure an…

• Coverage Before Control: Route-Instruction Grounding and Steering for Controllable Retrosynthesis

  Xuemin Chen, Xiaozhuang Song, Xinjian Zhao, Yaoyao Xu, Tianshu Yu · 1. Oktober 2026

  Single-step retrosynthesis models are commonly evaluated by their ability to recover recorded reactions. In practice, chemists may need to choose among several precursor sets for the same product, for example to preserve a particular motif. Recovering a recorded answer alone does not establish this …

• Diversity Combining for Multi-Path LLM Reasoning

  Guangsheng Yu, Litianyi Zhang, Qin Wang, Xu Wang, Mingyuan Li, Shaoxiong Ji, Ren Ping Liu, Massimo Piccardi · 1. Oktober 2026

  Multi-path reasoning methods such as self-consistency (SC) sample $K$ reasoning paths and choose the most frequent answer. However, their gains quickly plateau as $K$ increases, and existing methods do not predict when this saturation will occur. We formalize multi-path LLM reasoning as a diversity …

• Concept-Grounded Attention: A Controlled Evaluation of Graph-Injected Attention, Temporal Versioning, and Epistemic Status

  Sachin Dev Duggal, Pradyumna Swarnalatha Ramanna, Alexandros Vassiliades · 1. Oktober 2026

  Knowledge-intensive language-model systems typically represent external knowledge as text chunks or static graphs, with limited support for concept evolution, point-in-time reasoning, and distinctions between validated and inferred knowledge. We introduce the Concept Lifecycle Model (CLM), which rep…

• ArgGYM: A Procedural, Engine-Verified Benchmark for Structured Defeasible Reasoning

  \.Ibrahim Ethem Deveci, Funda Tan \c{C}al{\i}k, Bar{\i}\c{s} Deniz Sa\u{g}lam, Duygu Ataman · 1. Oktober 2026

  Recent progress in large language model reasoning has been driven by benchmarks and reinforcement learning environments with automatically verifiable rewards, particularly in mathematics, code, and formal logic. These settings make model accuracy easier to evaluate and optimize, but it remains uncle…

• From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark

  Chao Lei, Nir Lipovetzky, Krista A. Ehinger, Yanchuan Chang · 30. September 2026

  Recent reasoning-oriented LLMs have demonstrated strong performance on challenging tasks such as mathematics and science examinations. However, core cognitive faculties of human intelligence, such as abstract reasoning and generalization, remain underexplored. To address this, we evaluate recent rea…

• Rewarding Novel Deductions: Solver-guided Process Rewards for Logical Reasoning

  Muhammad Asif Ali, Wenqing Wang, Huan Wang, Mohammad Raza · 30. September 2026

  Logical reasoning remains a major challenge for large language models (LLMs), particularly on structured problems that require precise constraint tracking, consistency preservation, and multi-step deduction. This challenge is especially acute for small-scale LLMs, which are more prone to producing i…

• LLM-Guided Ontology-Driven Knowledge Graph Construction from Unstructured Text

  Abdelhadi Belfadel, Maxence Gagnant, Joseph Kattan, Sana Tmar · 30. September 2026

  Ontology-driven knowledge graph construction from industrial text remains challenging due to the domain specificity of documents, the scarcity of annotated resources, and the complexity of ontology engineering workflows. This paper presents and investigates the applicability of an ontology learning …

• Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces

  Ratish Puduppully, Pranabendu Misra, Paarth Iyer, Durgesh Kalwar, Vardhan Palod, Subbarao Kambhampati · 30. September 2026

  Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning. Testing this interpretation is difficult because natural-language thinking traces are rarely mechanically verifiable. We revisit it in iGSM, a synthe…

• $S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient

  Hongbo Ma, Sansheng Cao, Jiajun Fan, Bangji Yang, Ge Liu · 30. September 2026

  LLMs trained with Chain-of-thought excel in reasoning capability, but often come with excessive token cost. We find that the core of reasoning capacity lies in the Thinking model's weight component within the null space of a projection defined by the corresponding Non-thinking model's dominant singu…

• Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR

  Doohyuk Jang, Yoonsik Park, Gyouk Chu, Sihwan Park, Eunho Yang · 30. September 2026

  Reinforcement Learning with Verifiable Rewards (RLVR) methods such as GRPO rely on successful self-generated trajectories, but finite rollout budgets can produce all-fail groups with no reward-based policy-gradient signal. While additional rollouts improve the chance of success at higher cost, succe…

• DatalogBench: Evaluating Large Language Models on Text-to-Datalog Synthesis

  Yuan Li, Hanyun Jiang, Guowei Tian, Chengpeng Wang, Peisen Yao · 30. September 2026

  Datalog underpins reasoning tasks such as program analysis, but its programs are hard to write. Existing synthesizers automate this task but require users to state their intent as input-output examples. Large language models (LLMs) suggest a more natural route, text-to-Datalog synthesis from a natur…

• SRJudge: Empowering Large Language Models with Selective Reasoning for Fine-Grained Knowledge Concept Tagging

  Zhiwei Yang, Jiahua Yang, Huiru Lin, Xing Chen, Quanlong Guan · 30. September 2026

  Knowledge concept tagging aims to assign specific concept or topic labels to educational content, which is essential for both educators and learners in traditional and online teaching practices. Recent work has explored large language models (LLMs) for this task, achieving promising performance. How…

• Causal and Interpretable Structures in LLM Compositional Tasks

  Gurbir Arora, Toni J. B. Liu, Jiajun Bao, Rapha\"el Sarfati, Christopher J. Earls · 30. September 2026

  Large language models are able to solve tasks whose answers depend on not only individual input tokens, but also on relations among them. How is such relational information represented and processed across transformer layers? We study activations from ensembles of prompts that require inferring rela…

• CRASM-Gate: Deterministic-First Constraint- and Role-Aware Semantic Mapping with Selective Model Assistance Across Heterogeneous Industrial Standards

  Kabeh Mohsenzadegan, Vahid Tavakkoli, Kyandoghere Kyamakya · 30. September 2026

  Industrial standards often encode the same engineering concept through incompatible hierarchies, identifiers, roles, and structural constraints, so the nearest lexical or embedding match can still be technically inadmissible. This article presents CRASM, a deterministic constraint- and role-aware se…

• Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge

  Zixing Jia, Yuhang Pan, Ni Ji · 30. September 2026

  Structural reasoning, the ability to recognize and make inferences over the relational structure between objects and concepts, is a hallmark of human cognition, yet prevailing methods often collapse relational topology into flat embeddings, cannot discover hidden structure and lack interpretability.…

• The Geometry of Logic: Stratification Induces Semantic Structure and Robust Reasoning

  Cristina V. Lopes, Yuangang Li, Justin Tian Jin Chen, Alberto Krone-Martins, Iris Ma, Md Rakib Hossain Misu · 29. September 2026

  Transformer-based language models perform well on symbolic tasks, yet it remains unclear whether they learn generalizable rules or rely on statistical shortcuts. Mechanistic studies link algorithmic behavior to structured internal representations, motivating the hypothesis that robust reasoning bene…

• Explaining Textual Entailment with Lexical Entailments: Using LLMs to Supply Lexical Relations for Formal Proofs

  Jorryt de Jong, Stefan Moraca, Ettore Cesari, Lasha Abzianidze · 29. September 2026

  Large Language Models (LLMs) are highly capable of natural language reasoning and appear to store a great deal of lexical knowledge, but it is still unclear how much of this knowledge they actually use when reasoning, and whether they use it in the right way. On the other hand, logic-based Natural L…

• Reasoning with Continuous Latent Diffusion

  Xiang Cheng · 29. September 2026

  Continuous diffusion generates complete reasoning solutions through iterative refinement in latent space. We introduce Latent Flow Reasoning Models (LFRMs), an ELF-based training and inference recipe. Our experiments show that accurate decoding alone does not ensure strong reasoning performance. We …

• Not All Thinking is Created Equal: Latent Reasoning Discovers a Recurrent Search Algorithm for Depth Generalization

  Huzi Cheng, Zhewei Zhang · 29. September 2026

  Large Language Models can perform multi-step reasoning and improve task performance through different forms of intermediate computation, from token-based traces to computation carried out in latent space. However, a question remains open: do these different forms of thinking rely on the same underly…

• 5W1H+Which: Context-Valid Semantic Indexing with Progressive Ontology Binding

  Yaxiao Liu (PwC China AI Center), Pengbo Liu (PwC China AI Center), Yiwen Liu (PwC China AI Center), Yihua Guan (PwC China AI Center), Jiaxing Song (Tsinghua University) · 29. September 2026

  Transforming raw data into queryable knowledge requires both early extraction of reusable information and explicit types, relations, and applicability conditions for particular tasks. If indexing selects content too early around a single business schema, later tasks may be unable to use information …