Skip to content

Fabricated absence: structural misdescription in the design of LLM-based assistants

Jul 2026 · AI and Ethics · Vol 6 · 0 citations · 40 references
Computer Science

TL;DR

It is argued that some answerability-relevant deficits may be produced by alignment and deployment regimes themselves, and designers should avoid durable closure of non-trivial paths toward answerability-relevant capacities as a routine means of securing compliance, while also avoiding fabricated presence and responsibility laundering.

View source

Similar papers

Preprint Aug 2026

TRACES: A Benchmark for Epistemic Reliability in Scientific Reasoning by LLMs

A probe corpus of 42 retracted, fraudulent, and pseudoscientific papers is paired with a methodology for eliciting and scoring single-shot model engagement with each paper's framing, indicating an urgent need for guardrail infrastructure for scientific deployment of language models.

V. Rodionov, Shamil Assylbekov · 0 citations
Conference 2026

When Verification Hurts: The Cost of Overriding Abstention in Two-Stage Web Agents

This study cautions against transplanting verification into grounding pipelines and identifies calibrated abstention as a property worth preserving and proposes an abstention-aware verifier that intervenes only under sufficient candidate coverage and confidence.

Duchen Li · 0 citations
Preprint Aug 2026

Walking on the DARKSIDE

The evidence supports an architectural claim: when an LLM forward pass is wrapped in an ontology-mediated auditing, structurally inevitable hallucination can be partially recovered.

A. Gangemi, E. Bottazzi · 1 citation
Review Aug 2026

OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review

OpenCodeReview is introduced, built on deterministic engineering for uncertain agents: rather than granting maximal freedom, determinism is injected at three deliberate pipeline points to address non-determinism in LLM code review systems.

Zhengfeng Li, Lei Zhang, Xian Wu et al. · 0 citations
Review Aug 2026

Judging Is Not Enumerating: Silent Omissions in LLM-Authored Acceptable Sets

This work measures the capability that role assumes and finds it lacking under the protocol the role is usually deployed with, one-shot greedy authoring with no test-time reasoning.

Wen-Hui Chen, Jian-Lin Chen, Zi-Yao Lin et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.