Context Clash is when you accrue new information and tools in your context that conflicts with other information in the prompt.

This is a more problematic version of Context Confusion: the bad context here isn’t irrelevant, it directly conflicts with other information in the prompt.

A Microsoft and Salesforce team documented this brilliantly in a recent paper. The team took prompts from multiple benchmarks and ‘sharded’ their information across multiple prompts. Think of it this way: sometimes, you might sit down and type paragraphs into ChatGPT or Claude before you hit enter, considering every necessary detail. Other times, you might start with a simple prompt, then add further details when the chatbot’s answer isn’t satisfactory. The Microsoft/Salesforce team modified benchmark prompts to look like these multistep exchanges:

All the information from the prompt on the left side is contained within the several messages on the right side, which would be played out in multiple chat rounds.

The sharded prompts yielded dramatically worse results, with an average drop of 39%. And the team tested a range of models – OpenAI’s vaunted o3’s score dropped from 98.1 to 64.1.

What’s going on? Why are models performing worse if information is gathered in stages rather than all at once?

The answer is Context Confusion: the assembled context, containing the entirety of the chat exchange, contains early attempts by the model to answer the challenge before it has all the information. These incorrect answers remain present in the context and influence the model when it generates its final answer.

FROM:

Drew Breunig

How Long Contexts Fail

Source

It might be better to collect inputs and re-assemble them into a single prompt with a new context window, to prevent bias toward an incomplete initial response.

He has a follow-up article that is basically a list of ways to reduce context windows (either ahead of the prompt or following completion of a prompt/action).