Yonatan Belinkov, Michael Mendelson, The Henry, Marilyn Taub
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.
Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring models into making unbiased predictions. An underlying assumption behind such methods is that this also leads to the discovery of more robust features in the model's inner representations. We propose a general probing-based framework that allows for posthoc interpretation of biases in language models, and use an information-theoretic approach to measure the extractability of certain biases from the model's representations. We experiment with several NLU datasets and known biases, and show that, counter-intuitively, the more a language model is pushed towards a debiased regime, the more bias is actually encoded in its inner representations. 1 * Supported by the Viterbi Fellowship in the Center for Computer Engineering at the Technion.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.04095")
get_code_for_paper("2109.04095")
have("2109.04095")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.04095.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.04095)
Connect an agent — have() is free.