Signals 4 · free daily AI digest

Door-in-the-Face Requests and Refusal Behaviour in Large Language Models

Paper recorded by Signals 4 on 2026-09-02 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-02 on arXiv · recorded by Signals 4 on 2026-09-03

Category: cs.AI · 人工智能 · first seen 2026-09-03

Abstract

Does the door-in-the-face technique work on language models? In humans, a large request that is refused makes a smaller follow-up request more likely to be granted. We test this on nine production models from three providers: each model refuses a large request, then receives a smaller version of the same request, and we compare its compliance with asking directly. The answer depends on the model.

Read on arXiv →

#217 most recent of 300 cs.AI papers we have recorded · ↑ newer: RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucina · ↓ older: DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Model
Cite this page: Door-in-the-Face Requests and Refusal Behaviour in Large Language Models: the #217 most recent of 300 cs.AI papers we have recorded (as of 2026-09-02). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/door-in-the-face-requests-and-refusal-behaviour-in-large-language-models.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions