PulseAugur
EN
LIVE 16:50:59

Open-weight models pad JSON extraction lists, study finds

By PulseAugur Editorial · [1 sources] ·

A new study published on arXiv investigates how open-weight language models handle JSON extraction tasks when a schema specifies a minimum number of list entries. Researchers found that models tend to pad their output lists to meet or exceed this minimum, even when the source document contains fewer items. This padding is difficult to detect as models often use real text from the document for the extra entries. Standard fixes, such as indicating fewer items are acceptable or providing an "N/A" option, only partially mitigate the over-counting issue. AI

IMPACT Highlights a subtle but potentially significant flaw in how current open-weight models process structured data, impacting reliability in extraction tasks.

RANK_REASON Academic paper detailing a specific finding about model behavior. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Open-weight models pad JSON extraction lists, study finds

How we ranked this

Signal score
5 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Academic paper detailing a specific finding about model behavior. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · Abhishek Barali, Aayush Paudel ·

    Padding to k: A Minimum Count in the Schema Makes Open-Weight Models Pad Their Extraction Lists

    arXiv:2610.30997v1 Announce Type: new Abstract: Extraction pipelines ask language models for JSON that follows a schema, and the schema can set a minimum number of list entries. We ask what models do when the document holds fewer items than that minimum. Under a preregistered pla…

RELATED ENTITIES

RELATED TOPICS