OA‑RAG is an agent that combines formal ontology reasoning with large language model (LLM) reasoning to produce more faithful answers. For each response it lists the ontology observations used as evidence and assigns a grounding level—entailed, supported, related, or unrelated—to indicate the strength of that evidence. On benchmarks from three large ontologies and six real‑world medical QA tasks, OA‑RAG outperforms other ontology‑fine‑tuned and popular RAG methods, especially on reasoning‑intensive questions, and its grounding levels correlate with higher accuracy.
By Hui Yang, Jiaoyan Chen, Yongsheng Gao
arXiv:2608.31118v1 Announce Type: new
Abstract: The effect of Large Language Model (LLM) scale on ontology learning (OL) performance remains insufficiently characterized. We present a controlled eval...
By Hamed Babaei Giglou, S\"oren Auer, Jennifer D'Souza
arXiv:2607. 01977v1 Announce Type: new Abstract: Ontology learning (OL) aims to automatically construct structured knowledge models from text, yet progress remains fragmented across methods, domains, and evaluation practices.
By Hamed Babaei Giglou, Jennifer D'Souza, Andrei Aioanei, Nandana Mihindukulasooriya, S\"oren Auer
The paper presents an automated framework for building ontology networks by discovering typed semantic links between concepts across domains. It uses domain‑adapted DistilBERT embeddings, clustering to prune candidates, and GPT‑4o for generating interpretable relationships, reducing 800k raw pairs to 95k high‑quality candidates. Human validation on 429 links shows an 80.19% precision and 0.890 F1, outperforming five similarity‑based baselines and demonstrating the need for LLM reasoning in ontology link construction.
By Nouha Hayouni, Sheeba Samuel, Alsayed Algergawy
arXiv:2608.22974v1 Announce Type: new
Abstract: Large language model (LLM) agents rely heavily on knowledge encoded in model parameters or presented as unstructured context. In domain-specific tasks,...
By Xiaohui Zhang, Zequn Sun, Chengyuan Yang, Yuanning Cui, Lingbing Guo, Wei Hu
arXiv:2604.17614v2 Announce Type: replace-cross
Abstract: Skills are a natural unit for describing what a language model can do and how its behavior can be changed. However, existing characterization...
By Feiyang Kang, Mahavir Dabas, Myeongseob Ko, Ruoxi Jia
The paper introduces Integrated Policy Gradient (IPG), a training‑free framework that applies policy‑based attribution to large language model reasoning. IPG backpropagates outcome‑level, non‑differentiable signals through entire inference trajectories, using path integration to isolate outcome‑relevant mediators at the component level. Empirical results show that IPG precisely localizes sparse internal components linked to specific reasoning behaviors and enables modulation of reasoning capabilities.
By Changming Li, Kaixing Zhang, Haoyun Xu, Yingdong Shi, Zheng Zhang, Kaitao Song, Kan Ren
The paper investigates how large language models perform propositional logical reasoning by conducting a causal mechanistic analysis on the PropLogic-MI benchmark. It identifies four interlocking mechanisms—Staged Computation, Information Transmission, Fact Retrospection, and Specialized Attention Heads—that organize the reasoning process across layers. The study demonstrates that these mechanisms recur across different model families, rule categories, and reasoning hops, indicating a structured, layer‑organized internal process for propositional reasoning.
By Danchun Chen, Qiyao Yan, Chenpeng Wang, Liangming Pan
arXiv:2609.26610v1 Announce Type: new
Abstract: Despite their outstanding performance on many NLP tasks, LLMs face serious challenges related to semantic abstraction. In this study, we are interested...
By David Torres-Moreno, Jorge Hermosillo-Valadez
arXiv:2602. 20094v2 Announce Type: replace Abstract: As large language models (LLMs) witness increasing deployment in complex, high-stakes decision-making scenarios, it becomes imperative to ground their reasoning in causality rather than spurious correlations.
By Yuzhe Wang, Yaochen Zhu, Jundong Li
The study demonstrates that large language models (LLMs) can perform numerical prediction on tabular data by leveraging semantic grounding—matching variable names to the values they describe—without task-specific training. Across 20 datasets from nine scientific domains, five LLMs matched or outperformed seven supervised machine learning models, especially when training examples were scarce. Controlled experiments with physical formulas reveal that LLMs combine domain knowledge (as a prior) with in-context examples (likelihood) in a Bayesian‑like manner, adjusting predictions as contradictory examples accumulate.
By Xin-Rui Ma, Shi-Zhi Chen, Hai-Yan Jiang, De-Cheng Feng, Michael Beer
LMEnt is a toolkit designed to study how language models acquire and represent world knowledge. It includes a richly annotated pretraining corpus, an improved entity-based retrieval method, and twelve pretrained models with numerous checkpoints. The suite enables controlled experiments linking entity mentions in training data to downstream knowledge performance, revealing how co-occurrence patterns influence learning and editing difficulty.
By Daniela Gottesman, Alon Gilae-Dotan, Ido Cohen, Yoav Gur-Arieh, Marius Mosbach, Ori Yoran, Mor Geva