I wonder if the dip is more about LLama3 70b training and data than a change in sentiment. The data cut-off was Dec 2023 for 70b. That looks to coincide with the reversal of the dip.
That's an interesting hypothesis but the words we use to express agreement and disagreement haven't changed much.
We don't try to retrieve articles/topics from the model, which would be affected by the cutoff, just asking it to analyze the sentiment or summarize the content provided in a prompt
True. It would be interesting to run these same tests on the 7B model to see if trend information changes or not. 7B had a march cutoff so if the aug-dec dip migrated to oct-march (or just disappeared) it would be strong evidence for training/data bias. If nothing else, comparing 7B to 70B would likely be interesting.
edit I realized too late I had the years off. It is pure coincidence of month, not a real data bias. Sorry! I still think it would be interesting to see a 7B comparison but that is just to see how well a small model could spot big trends compared to a bigger one.
We don't try to retrieve articles/topics from the model, which would be affected by the cutoff, just asking it to analyze the sentiment or summarize the content provided in a prompt