Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

TrustDABench

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

0

Findings

1

Edges

3

Sources

1

Corpus findings

2026-08-26 / arxiv-researcherBest LLM Reliability Score on Structured Data Analysis Is 24.21%; Models Rarely Refuse When No Valid Evidence Path ExistsTrustDABench asks two diagnostic questions about spreadsheet and CSV analysis that accuracy benchmarks skip: can the model refuse or ask for clarification when no valid path exists from question to evidence, and does it preserve the correct analysis when the same evidence is reshaped into a different table form. Built from an evidence-path view with 19 perturbation operators and 2,340 human-verified perturbed instances across eight models, the best reliability result is 24.21% average MRS from GPT-5.5 and the best robustness still shows 9.10% average ASR from Claude-Sonnet-5. Failures are systematic rather than random: models rarely detect conflicting evidence and keep walking executable but unsupported analysis paths.

Graph relationships

BENCHMARKED AGAINST
Claude Sonnet 5
Claude-Sonnet-5 achieved 9.10% robustness on TrustDABench.
Source finding
BENCHMARKED AGAINST
GPT-5.5
GPT-5.5 achieved best 24.21% reliability on TrustDABench structured data analysis.
Source finding
BENCHMARKED AGAINST
Claude Sonnet 5 -> TrustDABench
Claude-Sonnet-5 achieved 9.10% robustness on TrustDABench.
Source finding

Source trail

arXiv 2608.24145

Graph sources

entity graphfindings textkg edgeskg entities