Beyond the Final Prompt: Measuring the Effect of Within-Conversation Context on AI Answers
2026-08-03 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors investigated if including earlier conversation parts changes AI answers compared to using only the last message from a user. They tested 180 multi-turn chats and found that nearly half the time, answers differ in important ways when earlier context is included. Summarizing just a part of the earlier conversation helps, but still misses some differences. Their work shows that to fully understand and respond well, AI benefits from the full conversation, not just the final user input.
multi-turn conversationcontext windowAI evaluationanswer qualityinverse-probability weightingbootstrap confidence intervalrequest satisfactionprompt compressiondialogue contextkappa statistic
Authors
Benjamin Tannenbaum
Abstract
An isolated final user message is often treated as the query in evaluations of AI systems. In a conversation, however, the actionable request may be distributed across preceding turns. We directly test whether that omitted within-conversation context changes answers. For each of 180 English multi-turn conversations sampled from a governed commercial corpus and the public PRISM dataset, we hold the final user message and requested answer model constant while generating three answers: one from the full role-labelled conversation, one from the final message alone, and one from the final message plus a prefix-only reconstruction capped at 160 words. A separately requested judge model evaluates answers under randomized labels. The prespecified primary endpoint is a material difference that could change what the user does, rather than a difference in style or detail. After inverse-probability weighting to the eligible cohorts, the full-conversation and isolated-final answers differ materially in 44.7% of cases (95% bootstrap CI 33.8% to 56.1%). Full-conversation answers score 0.49 points higher on a 0 to 4 request-satisfaction scale (0.32 to 0.67). Adding the compressed prefix reduces the material-difference rate to 30.8% (20.2% to 42.1%), a 13.9-point reduction (4.9% to 24.1%), and reduces the mean satisfaction gap to 0.01 points (-0.12 to 0.13). Yet compression is not equivalent to the complete dialogue context: almost one third of answers remain materially different. An order-swapped repeat on 48 cases yields 91.7% agreement and kappa = 0.83 for the primary decision. The study concerns preceding turns in the same conversation and does not test persistent memory across separate conversations.