Yoon Kim, James Glass, Tianxing He, Jiabao Ji
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The finetuning of pretrained transformer-based language generation models are typically conducted in an end-to-end manner, where the model learns to attend to relevant parts of the input by itself. However, there does not exist a mechanism to directly control the model's focus. This work aims to develop a control mechanism by which a user can select spans of context as "highlights" for the model to focus on, and generate relevant output. To achieve this goal, we augment a pretrained model with trainable "focus vectors" that are directly applied to the model's embeddings, while the model itself is kept fixed. These vectors, trained on automatic annotations derived from attribution methods, act as indicators for context importance. We test our approach on two core generation tasks: dialogue response generation and abstractive summarization. We also collect evaluation data where the highlight-generation pairs are annotated by humans. Our experiments show that the trained focus vectors are effective in steering the model to generate outputs that are relevant to user-selected highlights.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.01146")
get_code_for_paper("2203.01146")
have("2203.01146")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.01146.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.01146)
Connect an agent — have() is free.