• The bias traces to one specific routing signal: input length. Non-standard registers omit function words and so read as shorter and simpler to the router, while other complexity signals tested don't carry this effect.
• Every tier of the device-edge-cloud model ladder tested, including a frontier cloud model, answers non-standard-register queries significantly less accurately — the harm comes from bias present in every model, not just from routing to a weaker tier.
• The marginal quality cost of the routing decision itself was not statistically significant on this benchmark — routing compounds a bias that already exists in every model rather than being the primary source of harm.
• The disparity was demonstrated on 37,704 authentic learner sentence pairs plus a separate controlled parallel corpus, giving both real-world and controlled evidence for the same effect.

• LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
• benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.

If your product routes queries to cheaper models based on estimated complexity, this identifies a specific, measurable bias against non-standard English speakers baked into that routing signal.

• articleWho Do Language Models Think Is Competent? A Mechanistic Analysis of Occupational BiasKeren Fuentes, Aaron Mueller
• articleSelf- and Other-Labels Induce Bidirectional Bias in LLM JudgesSongeun Chae, Min Kim, Donghoon Jung, Seojin Choi, Seohyon Jung
• articleRFCLLM: Evaluating LLMs' Reasoning Ability of Network Protocol State MachinesAnqi Chen, Dan Goldwasser, Cristina Nita-Rotaru

Checking sign-in…

Loading comments…