5-Air across ten knowledge domains at temperature zero.
Models Follow False Conversation History According to Its Apparent Authority
Tests across three language models found sharply different rates of adopting the same false premise when its attributed source or instructional force changed.
Industry
Fahrell Giovanny · Geby Bayuningtyas · Sahrul Mukharom · Hafiz Budi Firmansyah
Independent Researcher · Institut Teknologi Sumatera
Research Digest··2 min read
The authors injected false premises into multi-turn conversations using five protocols spanning self-attribution, cited sources, system authority and instruction overrides.
Why this paper
From Independent Researcher and Institut Teknologi Sumatera
In one line
LLMs show divergent epistemic policies: GPT-5.4 Mini resists false premises, Gemini follows authority gradient, GLM shows shallower gradient.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ✓Reports numbers on named benchmarks (2 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§