PL
P.S. Lekkerkerker
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
Evaluating the Value-Action Gap in Small Language Models using Moral Foundations Theory
The Impact of Moral Persona Prompting on Behavioral Alignment
As Language Models (LMs) are deployed in high-stakes environments, mitigating the "Value-Action Gap", the discrepancy between an LM's stated values and its actual behavior, is critical. While prior work highlights how this gap varies across cultures, it does not investigate methods to systematically mitigate this misalignment using structured moral profiles. To address this, we use Moral Foundations Theory (MFT) to evaluate whether prompt-engineered moral personas can anchor an LM's concrete actions to abstract Schwartz values. Evaluating Llama 3.2-1B, Gemma 2-2B, and Qwen 2.5-3B on a new dataset of 616 scenarios across 11 social contexts, we split our evaluation into measuring abstract value inclinations and concrete situational actions. We then analyze value-action alignment across 64 moral configurations against an unprompted baseline. Our findings show that MFT profiling fails to universally close the gap. Alignment is highly architecture-dependent, revealing a sharp divergence between distance optimization and cross-task consistency. While some models show widespread improvement, others resist change unless triggered by highly specific configurations like isolated HIGH Care. Ultimately, prompt-engineered personas cannot reliably override an architecture's underlying behavioral priors, meaning small models remain unreliable for value-aligned tasks without explicit action tuning.
...
As Language Models (LMs) are deployed in high-stakes environments, mitigating the "Value-Action Gap", the discrepancy between an LM's stated values and its actual behavior, is critical. While prior work highlights how this gap varies across cultures, it does not investigate methods to systematically mitigate this misalignment using structured moral profiles. To address this, we use Moral Foundations Theory (MFT) to evaluate whether prompt-engineered moral personas can anchor an LM's concrete actions to abstract Schwartz values. Evaluating Llama 3.2-1B, Gemma 2-2B, and Qwen 2.5-3B on a new dataset of 616 scenarios across 11 social contexts, we split our evaluation into measuring abstract value inclinations and concrete situational actions. We then analyze value-action alignment across 64 moral configurations against an unprompted baseline. Our findings show that MFT profiling fails to universally close the gap. Alignment is highly architecture-dependent, revealing a sharp divergence between distance optimization and cross-task consistency. While some models show widespread improvement, others resist change unless triggered by highly specific configurations like isolated HIGH Care. Ultimately, prompt-engineered personas cannot reliably override an architecture's underlying behavioral priors, meaning small models remain unreliable for value-aligned tasks without explicit action tuning.