The paper introduces “Rel-Bloom,” a multilingual diagnostic benchmark of 450 multiple-choice questions that tests language models’ ability to reason over relational facts supplied directly in prompts. It evaluates 43 models across six languages and two multilingual settings, revealing that accuracy drops sharply from Apply to Analyze levels, that Evaluate items remain a bottleneck even for high-performing models, and that difficulty rankings are consistent across languages. The study also finds that counterfactual contexts are generally harder than factual ones, and that removing entity identities can sometimes improve higher-level performance.
By Zohreh Abbasi Liasi, Batoul Hammoud, Anas Madkoor, Ehsaneddin Asgari
arXiv:2607. 13568v1 Announce Type: cross Abstract: Can a language model estimate its familiarity with an entity before generating an answer?
By Grzegorz Brzezinka
The study evaluates whether prompt‑token counts can reliably identify the lineage of large language models served via APIs. Using a frozen‑threshold approach on 24 labeled endpoint pairs, the authors find that token‑count consistency perfectly separates development pairs but only half of the holdout pairs meet the strict repeatability criteria, yielding moderate accuracy and perfect specificity. The results confirm token‑count consistency as a fingerprint of shared tokenization stacks but reject it as a standalone test for model‑family attribution.
By Bo Chen
arXiv:2603.13911v2 Announce Type: replace
Abstract: A language model can give the wrong answer even when the correct answer is decodable from its intermediate states. To study this gap between decoda...
By Valeria Ruscio, Keiran Thompson
MechaTerp-TRACE is a new framework that systematically ablates individual components of language models to measure their causal contribution to producing a named entity. By applying TRACE to thirteen instruction‑tuned dense decoder models, the study finds that a small set of positionally fixed components consistently carry the most influence across models and prompts, while the remaining support is evenly distributed. This suggests that entity knowledge is largely embedded in generic generation machinery rather than in isolated, findable components.
By Brandon Colelough, Davis Bartels, Madeline Bittner, Dina Demner-Fushman
arXiv:2603. 00270v3 Announce Type: replace-cross Abstract: Large language models can process millions of tokens, yet how they handle conflicting information within context remains poorly understood.
By Sourav Chattaraj, Kanak Raj
arXiv:2605.12922v2 Announce Type: replace
Abstract: Large language models can follow complex instructions in a single turn, yet over long multi-turn interactions they often lose the thread of instruc...
By Vardhan Dongre, Joseph Hsieh, Viet Dac Lai, Seunghyun Yoon, Trung Bui, Dilek Hakkani-T\"ur
arXiv:2607. 19257v1 Announce Type: cross Abstract: Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade.
By Netanel Eliav
The paper investigates when a language model actually learns task information versus when its readout (unembedding matrix) learns to express that information. Using a new parameter‑trajectory cross‑coding method, the authors find that hidden states can encode task data early in training, but the readout reorganizes only in a narrow window (0.4–1.1% of Pythia’s pretraining). By varying the readout learning rate, they show that faster readout learning reduces the gap between hidden‑state encoding and output expression without affecting final performance.
By Matteo He, William F. Shen, Alex Iacob, Andrej Jovanovic, Xinchi Qiu, Nicholas D. Lane
arXiv:2610.18674v1 Announce Type: cross
Abstract: Large language models rely on prompt context to perform in-context learning, follow formats, and adapt to local evidence. This ability, however, also...
By Jinghan Zheng, Jiajun Shi
arXiv:2608. 04021v1 Announce Type: cross Abstract: Cloze-style probes that vary how often a target token appears implicitly assume that more copies of a target affect prediction the same way regardless of where the readout slot sits.
By Han-yu Wang
Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade. We report two controlled experiments crossing all three factors on one held, contamination-free synthetic corpus (the "Book of Veyra," 8,780 uniquely-named entities, deterministically regenerable from a fixed seed), evaluated across five models.