The paper proposes a model-based evaluation framework that merges multidimensional item response theory (IRT) with question context embeddings to predict large language model (LLM) performance on unseen questions. By representing LLMs with latent capability profiles and incorporating question content to inform item characteristics, the approach improves prediction accuracy over model-free baselines in within-scenario settings and offers a richer description of capability variation than unidimensional models. However, the study also finds that this generalizability does not reliably extend to cross-scenario shifts, indicating a key limitation for broader application.
By Ergan Shang, Weijing Tang, Yinqiu He
The paper introduces Intelligent Target Locator (ITL), a method that measures how well a document aligns with concepts in a Structured Reference Document (SRD) by creating concept‑specific term profiles and computing a textual‑unit–concept affinity matrix. ITL assigns importance weights to terms based on concept membership, term specificity, and discriminability, enabling traceable, quantitative alignment scores at multiple granularity levels. An internal consistency test on the 17 Sustainable Development Goals showed that each goal statement achieved its highest affinity with its corresponding concept, demonstrating ITL’s ability to distinguish conceptual profiles.
By Ra\'ul Gir\'aldez, Dayrelis Mena, Jes\'us S. Aguilar--Ruiz
arXiv:2608. 06609v1 Announce Type: new Abstract: Automated item evaluation (AIE) refers to the use of computational methods to assess item quality without requiring manual expert review or field testing of the items under evaluation.
By Hotaka Maeda, Yikai Lu
arXiv:2609.09004v1 Announce Type: cross
Abstract: Large Language Models (LLMs) demonstrate impressive performance across diverse NLP tasks, yet their ability to exhibit genuine contextual understandi...
By Subavarshana Arumugam, Mamta Nallaretnam, Kithuni Wickramasinghe, Chamath Gunapala, Pragatheeswaran Vipulanandan, Uthayasanker Thayasivam, Kamal Premaratne
arXiv:2608. 07208v1 Announce Type: cross Abstract: Existing measures of how much a text is about a concept read the surface of the text: dictionary word shares, topic proportions, embedding similarities.
By Luc Hazenoot, Zhaochun Ren, Amirhossein Zohrehvand
arXiv:2608. 05726v1 Announce Type: cross Abstract: Large Language Models (LLMs) are often used as evaluators of text quality, known as LLM-as-a-Judge, which can outperform conventional automatic evaluation metrics that rely on reference texts.
By Yuma Asato, Kiyoaki Shirai, Natthawut Kertkeidkachorn
Large Language Models (LLMs) are often used as evaluators of text quality, known as LLM-as-a-Judge, which can outperform conventional automatic evaluation metrics that rely on reference texts. However, LLM evaluators tend to generate particular scores regardless of the context of the evaluated text, which is known as scoring bias.
The article examines how AI‑assisted item generation is filtered by a computational evaluator before expert review, focusing on representation, structural screening, and candidate‑form dependence. Through two in‑silico studies of 32,000 Big Five items, the authors show that subtle differences in semantic representation and structural evaluation lead to divergent item selections, even when overall content coverage appears stable. The findings reveal that the evaluator, often treated as a neutral technical step, actually shapes the evidence and wording that psychometricians ultimately review, highlighting its role as a revisable component of measurement design.
By Christopher Brooks (School of Information, University of Michigan)
The paper introduces a knowledge‑graph‑based evaluation framework, S3KG, to assess whether large language models truly understand context in question answering tasks. S3KG combines structural and semantic signals into a single similarity score and is paired with a diagnostic analysis that pinpoints reasoning errors at the triplet level. Across nine benchmarks, the method outperforms existing baselines, achieving up to +7.6 F1 points and an AUROC of 0.973.
By Subavarshana Arumugam, Mamta Nallaretnam, Kithuni Wickramasinghe, Chamath Gunapala, Pragatheeswaran Vipulanandan, Kamal Premaratne, Uthayasanker Thayasivam
arXiv:2610.09063v1 Announce Type: new
Abstract: Multi-label topic assignment for user-generated content (UGC) -- including product reviews and buyer-seller conversations -- poses unique scalability c...
By Sourabh Kasliwal, Shubhranshu Singh
The paper introduces the concept of LLM‑specific utility, defining it as the performance gain a target large language model (LLM) achieves when provided with a passage compared to answering without evidence. A benchmark of utilitarian passages is built for four LLMs (Qwen3‑8B/14B/32B and Llama 3.1‑8B) across three QA datasets, revealing that each model benefits most from its own tailored evidence and that evidence optimized for other models is consistently suboptimal. The authors also create SpecUBench, a benchmark for LLM‑specific utility judgment, and show that current utility‑aware retrieval methods largely capture model‑agnostic usefulness, struggling to estimate LLM‑specific utility.
"whyItMatters":"The study demonstrates that retrieval‑augmented generation must consider model‑specific evidence selection to truly improve LLM performance, highlighting a gap in existing utility‑aware methods."
By Hengran Zhang, Keping Bi, Jiafeng Guo, Jiaming Zhang, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng
arXiv:2606. 00467v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-internalized priors interact with user-provided instructions.
By Etienne Casanova, Rafal Kocielnik, R. Michael Alvarez