The paper evaluates Laya, a small model that processes a multiple‑choice question, its options, and a text in a single 512‑token sequence. Experiments show that when the relevant evidence lies beyond the window, accuracy drops to about 26–27%, and confidence metrics fail to warn of truncation. Fine‑tuning on longer documents improves performance on visible evidence but not on cut evidence, and a larger window or a 312‑token scan can yield modest gains.
By Mohammed Nayeem Khan, Allan Kevin T
The study investigates how the composition of data during the mid‑training phase of language models affects performance across multiple domains. Experiments with Qwen3‑8B‑Base on five distinct KOR‑Bench domains show that moderate coverage (10%‑40%) yields the best per‑domain results, and that alignment passes cannot fully close the performance gaps created by mid‑training data choices. Additionally, zero coverage in mid‑training severely degrades accuracy, while a carefully tuned allocation can provide the largest overall pipeline improvement.
By Yunpeng Xu, Kun Zheng
The paper investigates how per-domain data composition during the mid‑training phase (between pre‑training and alignment) affects model performance. Experiments with Qwen3‑8B‑Base across five KOR‑Bench domains show that a moderate coverage band (10%‑40%) yields the best performance for each domain, and that alignment passes cannot fully close the gaps created by suboptimal mid‑training allocations. Additionally, zero coverage during mid‑training severely degrades accuracy, while a carefully tuned allocation can provide the largest overall pipeline improvement.
The paper presents a system for the MedReason 2026 challenge that tackles both multiple‑choice and open‑ended medical visual question answering using offline, containerized inference. Key findings include that comparing answer semantics rather than labels boosts retrieval‑only accuracy from 20.0 % to 57.5 % on a 200‑case holdout, and that varying the number of in‑prompt retrieved examples has minimal impact on final accuracy (93.5 %–94.0 %). The final system achieves 94.0 % MCQ accuracy on the development set and 93.20 % on the official pre‑evaluation, far surpassing the off‑the‑shelf baseline.
"whyItMatters":"The results demonstrate that semantic‑aware retrieval and careful adapter tuning can dramatically improve medical VQA performance, offering a practical approach for high‑accuracy, offline inference in clinical settings."
By Tristan Kirscher (ICube, Institut Strauss), Niklas C. Koser (CAU), Soren Pirk (CAU)
arXiv:2610. 29052v1 Announce Type: cross Abstract: A typed decision maps evidence, a question and a fixed set of options to a probability for every option, computed in one forward pass, by reading a language model's logits or a small head over its hidden states, instead of generating and parsing text.
By Yuchuan Weng, Chi Liu, Xin Chen, Srinivasan Manoharan
The paper presents a practical five‑step recipe for recalibrating a typed‑decision model (Laya) that assigns confidence scores to text classification options. Using 130 lines of NumPy, the authors demonstrate that per‑bucket temperature scaling significantly reduces both pooled and macro‑ECE on a Turkish model, outperforming global scaling and other calibration methods. The study shows that separating buckets and applying bucket‑specific temperature adjustments yields the largest gains in accuracy and confidence calibration.
By Mohammed Nayeem Khan, Aliyas Ahmad Misri
arXiv:2610.14707v2 Announce Type: new
Abstract: Expert-aligned "taste" benchmarks should reward craft judgment, not the ability to game the test. We introduce TasteBench, a pairwise good-vs-bad bench...
By Xiaofan Wu, Xi Zeng, Miaoxia Chen, Peishan Chen, Shuyan Li, Chen Wang, Xiaohan Wang, Wanling Xu, Jiyun Yao, Hanyong Zhong, Jiahao Zhu
The paper compares a non‑generative verifier (Jev) with a frontier LLM (Astra) on 495 human‑labelled claims from LLM‑AggreFact. Both models achieve statistically indistinguishable accuracy, yet Jev is 187‑fold cheaper and admits more unsupported claims. A confidence‑gated cascade that escalates uncertain claims improves cost‑efficiency, though the benefit comes mainly from the escalation share rather than the probability estimates.
By Alden Do Rosario, Kirollos Atef
The paper evaluates how well typed decision models, which output probability distributions, actually provide reliable guarantees. By comparing open-weight Laya and Jev 1.13 across 190 evaluations, the study finds that point‑estimate thresholds frequently break promised accuracy, while a Beta lower‑bound rule and Learn‑then‑Test approach maintain guarantees more consistently. The work also explores calibration across languages, the impact of noise, data requirements for fine‑tuning, and the limitations of confidence in predicting outcomes or providing faithful explanations.
By Pedro Carvalho Brom
The paper investigates whether disagreement between two quantized versions of the same language model can serve as an error signal for tasks such as abstention and escalation. Using Qwen3-0.6B and Qwen3-1.7B, the authors compare an 8‑bit copy with lower‑precision copies (3–6 bits) on multiple-choice datasets, measuring error detection via AUROC, risk‑coverage, and ECE. Results show modest gains over entropy alone, with additional forward passes offering limited improvement, and the study provides a deployment recipe and discusses scenarios where the method is ineffective.
By Mohammed Nayeem Khan, Allan Kevin T
The study analyzes 373,019 judgments from LLM‑scored benchmarks, decomposing variance into system, item, judge, and interaction components via generalizability theory. It finds that with a single judge, generalizability converges to a ceiling determined by the system‑by‑judge variance, which is substantially lower in pairwise preference settings, allowing one judge to suffice. The research also reveals significant biases in presentation order and highlights that many published win‑rate claims fall below the measured floor of the benchmarks.
By Atul Anand
The paper evaluates cost‑aware abstention for routing IT support tickets, comparing four non‑LLM classifiers and four large language models on a 47,837‑ticket, eight‑class dataset. Using a cost model (c_ok=0, c_triage=1, c_wrong=5), a TF‑IDF logistic regression model with a 0.60 threshold reduced test cost from 0.763 to 0.472 and lowered wrong routes from 15.3% to 3.5%. The study also shows that calibration‑selected policies outperform always‑route and always‑defer strategies in most settings and introduces new metrics such as correctness AUROC and tie‑aware risk‑coverage area.
By Sachin Gupta