Skip to content
Series
2 posts

AI Common Failures

Patterns in LLM prose that read as informative but leave the reader without an answer: contrast framing, significance inflation, indicative summaries, overgeneralization. Each post covers how to spot it, how to fix it and when to keep it, followed by causes, guardrails and the risk of overcorrecting.

Series guide
aiguideAI Common Failures

AI Common Failures: Contrast Framing, Significance Inflation, Indicative Summaries, Overgeneralization

LLM prose has four recurring failures: contrast framing (refuting an X nobody said), significance inflation (dressing a plain fact up as a turning point), indicative summaries (announcing the topic, withholding the conclusion) and overgeneralization (summaries that drop conditions and scope). Fix the first three by cutting the filler and writing the answer; fix the fourth by checking each sentence against the source. Contrast framing has been traced to preference data, and models revising a draft move it into another contrast form, so banning a phrase in the prompt may not stop it.

#llm-writing#llm#writing-process
aideep-diveAI Common Failures

Fixing "It's Not X, It's Y": Three Forms of Contrast Framing, How Common It Is, and When to Keep It

Ask two questions of every contrast: do readers actually hold X, and does rejecting X tell them anything new? If either answer is no, drop X and state Y. 'Rather than' became about seven times as frequent in NLP papers from 2019 to 2026, and five commercial models writing Chinese use the equivalent construction 2.5–9.2 times as densely as a human reference corpus. Models almost never misuse it, but more than half the uses are unnecessary, and with eight in one paper, at least one tends to annoy the reader.

#llm-writing#llm#writing-process