Explaining novel senses using definition generation with open language models
This work addresses the challenge of explainable semantic change modeling for Finnish, Russian, and German languages, though it is incremental as it builds on existing shared task datasets and methods.
The researchers tackled the problem of explaining novel word senses by applying open-weights large language models as definition generators, achieving performance higher than the best submissions in the AXOLOTL'24 shared task that used closed proprietary LLMs, with encoder-decoder models performing on par with decoder-only ones.
We apply definition generators based on open-weights large language models to the task of creating explanations of novel senses, taking target word usages as an input. To this end, we employ the datasets from the AXOLOTL'24 shared task on explainable semantic change modeling, which features Finnish, Russian and German languages. We fine-tune and provide publicly the open-source models performing higher than the best submissions of the aforementioned shared task, which employed closed proprietary LLMs. In addition, we find that encoder-decoder definition generators perform on par with their decoder-only counterparts.