A team uses Claude with few-shot examples to perform sentiment analysis on product reviews. The model performs well on examples similar to the few-shot set but poorly on reviews with unusual phrasing or mixed sentiment. What is the most effective architectural improvement?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — the team's issue is distribution shift — their few-shot examples don't cover the edge cases encountered in production. The fix is to diversify examples to include the failure modes (mixed sentiment, sarcasm, ambiguous phrasing) and add chain-of-thought demonstrations that explicitly show the reasoning process for ambiguous cases.
Full explanation below image
Full Explanation
The team's issue is distribution shift — their few-shot examples don't cover the edge cases encountered in production. The fix is to diversify examples to include the failure modes (mixed sentiment, sarcasm, ambiguous phrasing) and add chain-of-thought demonstrations that explicitly show the reasoning process for ambiguous cases. This teaches Claude both the pattern and the reasoning strategy. Option A (more examples) helps only if the new examples cover the distribution gaps; quantity alone doesn't address quality gaps. Option C (zero-shot) removes the behavioral anchoring that few-shot provides — Claude's default sentiment analysis may be less calibrated to the specific product domain and review style. Option B invents an Anthropic fine-tuning API that is not a publicly available feature for Claude models in this exam's scope.