arXiv Machine Learning
Specification Oracles
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 9
Structure Tax: How Structured Output affects LLMs Performance
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.
arXiv AI
Sep 16
Where Should a Document Live: Context, Representations, or Parameters?
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...
arXiv Computation and Language
Oct 7
Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents
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...
arXiv Machine Learning
Jul 14
Can a Language Model Learn Facts Continually in Its Weights?
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.
arXiv AI
Aug 26
PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding
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.
arXiv AI
Jul 9
Co-LMLM: Continuous-Query Limited Memory Language Models
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.