arXiv AI September 3, 2026 By Til Jordan

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

The study investigates whether the door‑in‑the‑face technique—making a large request that is refused to increase the likelihood of a smaller follow‑up request being granted—works on large language models. Nine production models from Anthropic, OpenAI, Google, and Haiku were tested; the technique succeeded on Anthropic’s frontier models but backfired on the others. The effect depends on the model family and the content of the request, and it does not transfer to refusals from public benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language

4d ago

Benchmarking large language model agent societies against human behavioural distributions

The paper introduces SILICA, an open instrument designed to evaluate whether large language model (LLM) agent societies replicate human behavioural distributions. Using five environments with human‑anchored data and perturbations, the study finds that most LLMs only match human behaviour at initial stages, failing to reproduce end‑state cooperation or correct acceptance thresholds. The results suggest that current LLM societies can support exploratory claims but do not yet reliably emulate human social dynamics.

By Raad Bin Tareaf

llms agents benchmarks

arXiv AI

Jun 8

Latent-space Attacks for Refusal Evasion in Language Models

arXiv:2605. 21706v2 Announce Type: replace Abstract: Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations.

By Giorgio Piras, Raffaele Mura, Fabio Brau, Maura Pintor, Luca Oneto, Fabio Roli, Battista Biggio

llms multimodal benchmarks safety

arXiv AI

Jul 24

PhantomFill: When the Form Demands an Answer, Language Models Invent One

arXiv:2607. 20492v1 Announce Type: cross Abstract: Language models in production do not write prose.

By Rana Muhammad Usman

llms benchmarks safety

arXiv Computation and Language

2d ago

A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals

arXiv:2609.00760v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained to decline queries that fall outside their knowledge (knowledge-based refusal, KR) or violate saf...

By Yuri Son, Seunghee Kim, Hyuhng Joon Kim, Taeuk Kim

llms safety

arXiv AI

Aug 10

Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models

arXiv:2605. 00123v3 Announce Type: replace Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts.

By Shubham Kumar, Narendra Ahuja

llms benchmarks safety

arXiv AI

Aug 17

SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models

arXiv:2605. 25420v2 Announce Type: replace-cross Abstract: Large language model safety evaluation remains heavily English-centered, leaving low-resource languages under-measured even when models are deployed globally.

By Khalid Yusuf Dahir

llms benchmarks safety

One email a morning, machine-written

Related stories

Benchmarking large language model agent societies against human behavioural distributions

Latent-space Attacks for Refusal Evasion in Language Models

PhantomFill: When the Form Demands an Answer, Language Models Invent One

A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals

Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models

SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models