The paper investigates the so‑called ‘structure tax’ that is often attributed to constraining large language model outputs to structured formats like JSON or XML. By evaluating various models, datasets, and schema designs, the authors find that the accuracy loss depends more on how the schema is organized than on the presence of structure itself. Specifically, reasoning‑first field ordering can match or surpass free‑form accuracy, whereas answer‑first ordering leads to significant drops, especially in smaller models. The study also shows that well‑designed schemas improve confidence calibration and the separability of correct versus incorrect representations in transformer layers.
By Vineet Kumar, Kanishka, Bhuvanesh Mandora
arXiv:2609.17346v1 Announce Type: cross
Abstract: To answer questions outside of their pre-training data, large language models (LLMs) need access to new information, which can be presented in the co...
By Nathana\"el Carraz Rakotonirina, Momchil Hardalov, Gonzalo Iglesias, Adri\`a de Gispert
arXiv:2610.06650v2 Announce Type: replace
Abstract: Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right en...
By Mohamed Chenene, Carlos Rosas-Hinostroza, Anastasia Stasenko, Shani Evenstein Sigalov, Pierre-Carl Langlais
arXiv:2607. 11020v1 Announce Type: cross Abstract: Continual learning promises a language model that keeps acquiring knowledge after training, with each new fact written into its weights.
By Charles O'Neill
PARTAB is a framework that improves large language model reasoning on tables by constructing a structured evidence interface. It represents query‑relevant evidence as semantically coherent, row‑linked table regions and performs hierarchical selection over column groups and row‑level partitions before composing the evidence for answer generation. Evaluations on multiple table reasoning benchmarks show that PARTAB consistently outperforms full‑table prompting and recent methods, achieving strong performance on WikiTableQuestions and TabFact while remaining competitive on numerical reasoning tasks.
By Md Mahadi Hasan Nahid, Davood Rafiei
arXiv:2607. 07707v1 Announce Type: cross Abstract: Limited memory language models (LMLMs) externalize factual knowledge during pretraining to a knowledge base (KB), rather than memorizing it in their weights.
By Yair Feldman, Linxi Zhao, Nathan Godey, Dongyoung Go, Yilun Hua, Kilian Q. Weinberger, Jennifer J. Sun, Yoav Artzi
arXiv:2606. 10460v1 Announce Type: cross Abstract: Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can be trivially retrieved.
By Haonan Wang, Jiaxiang Liu, Yurong Liu, Austin Senna Wijaya, Tianle Zhou, Eden Wu, Yijia Chen, Wanting You, Reya Vir, Daniela Pinto, Grace Fan, Yusen Zhang, Juliana Freire, Eugene Wu
The paper introduces Highlight-Then-Summarize (H2S), a two-step approach that first highlights question-relevant evidence in long documents and then condenses it into a compact, question-conditioned summary before generating an answer. The authors built the H2S-Dataset with 6,647 examples spanning 11 benchmark families, and developed H2S-RL to reward evidence selection and summary construction. Evaluated on the H2S-Bench suite, the H2S-14B model outperforms larger open-source models, achieving the highest overall score and maintaining strong performance even with a reduced output budget.
By Zhaoyuan Xia (Peking University, Baidu Inc), Qinghongbing Xie (Tsinghua University), Yung Xiang Hue (Tsinghua University), Jianguang Jiang (Baidu Inc), Gaofeng Lu (Baidu Inc), Zhenyu Jiao (Baidu Inc), Xing Yuan (Baidu Inc), Dai Dai (Baidu Inc), Tong Mo (Peking University), Long Zeng (Tsinghua University)
arXiv:2608. 20106v1 Announce Type: new Abstract: We introduce OenoBench, a wine-domain knowledge benchmark of 3,266 multiple-choice questions across six pillars (regions, grape varieties, viticulture, winemaking, producers, business) and four difficulty tiers.
By Nikita Khudov
TeleTables is a benchmark that evaluates large language models on interpreting telecom tables from 3GPP specifications. It contains 2,220 tables in four formats and 500 human‑verified multiple‑choice questions that range from simple retrieval to multi‑step reasoning. Tests on 20 open‑weight LLMs show that closed‑book performance is limited by domain knowledge, while providing the table as context yields high accuracy that still drops with deeper reasoning, evidence scope, and structural complexity.
By Anas Ezzakri, Nicola Piovesan, Mohamed Sana, Antonio De Domenico, Fadhel Ayed, Haozhe Zhang
arXiv:2607. 17742v1 Announce Type: new Abstract: Tables are a critical knowledge source in retrieval-augmented generation (RAG), but a retrieved table may lack sufficient evidence to answer a query, a property we call answerability.
By Jiaming Tian, Liyao Li, Wentao Ye, Haobo Wang, Lihua Yu, Zujie Ren, Gang Chen, Junbo Zhao
Large Language Models (LLMs) have shown strong capabilities in table reasoning, but their effectiveness degrades as tables grow in size and complexity due to irrelevant context and difficulty localizi...