A fine-tuned LLM that generates explanatory reasons from career history before predicting the next occupation achieves better accuracy than standard approaches.
arXiv (2023)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Sink value vectors in Omni-LLMs act as a shared bias organizing token representations, and aligning non-sink tokens to them via OutRo improves performance on video QA benchmarks.
citing papers explorer
-
On Reasoning Behind Next Occupation Recommendation
A fine-tuned LLM that generates explanatory reasons from career history before predicting the next occupation achieves better accuracy than standard approaches.
-
On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs
Sink value vectors in Omni-LLMs act as a shared bias organizing token representations, and aligning non-sink tokens to them via OutRo improves performance on video QA benchmarks.