RL
R.W.J. Lakerveld
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
1 records found
1
Exploring the Value-Action gap
Language models and cultural-political personas
Large language models (LMs) frequently demonstrate a "value-action gap," explicitly endorsing specific moral values while simultaneously generating contradicting action recommendations in identical scenarios. This gap could be reduced by conditioning LMs with a persona defined by its cultural-political orientation, giving the LM sufficient context to consistently reason about the dilemma.
To analyze this, we introduce a dataset of moral dilemmas alongside a methodology to generate personas based purely on cultural variables of the Inglehart-Welzel Cultural map.
Our experiments reveal that conditioning LMs with these structured profiles generally reduces the value-action gap across all tested architectures. This improvement is most pronounced for internally consistent cultural-political orientations, both for moderate and more radical perspectives. However, language models continue to struggle significantly with internally incongruous personas. These findings underscore a persistent challenge in LM value reasoning. ...
To analyze this, we introduce a dataset of moral dilemmas alongside a methodology to generate personas based purely on cultural variables of the Inglehart-Welzel Cultural map.
Our experiments reveal that conditioning LMs with these structured profiles generally reduces the value-action gap across all tested architectures. This improvement is most pronounced for internally consistent cultural-political orientations, both for moderate and more radical perspectives. However, language models continue to struggle significantly with internally incongruous personas. These findings underscore a persistent challenge in LM value reasoning. ...
Large language models (LMs) frequently demonstrate a "value-action gap," explicitly endorsing specific moral values while simultaneously generating contradicting action recommendations in identical scenarios. This gap could be reduced by conditioning LMs with a persona defined by its cultural-political orientation, giving the LM sufficient context to consistently reason about the dilemma.
To analyze this, we introduce a dataset of moral dilemmas alongside a methodology to generate personas based purely on cultural variables of the Inglehart-Welzel Cultural map.
Our experiments reveal that conditioning LMs with these structured profiles generally reduces the value-action gap across all tested architectures. This improvement is most pronounced for internally consistent cultural-political orientations, both for moderate and more radical perspectives. However, language models continue to struggle significantly with internally incongruous personas. These findings underscore a persistent challenge in LM value reasoning.
To analyze this, we introduce a dataset of moral dilemmas alongside a methodology to generate personas based purely on cultural variables of the Inglehart-Welzel Cultural map.
Our experiments reveal that conditioning LMs with these structured profiles generally reduces the value-action gap across all tested architectures. This improvement is most pronounced for internally consistent cultural-political orientations, both for moderate and more radical perspectives. However, language models continue to struggle significantly with internally incongruous personas. These findings underscore a persistent challenge in LM value reasoning.