Papers for

survey analysts

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Large language models balance what they say and what they know better

Speak vs. Know: Balancing Behavior and Knowledge Distributions of Large Language Models

Abstract: Recent work reports that the distribution verbalized directly in the output text aligns far better with human opinion distributions than the next-token log-probability distribution of LLMs. However, the verbalized distribution reflects what LLMs know about a group's opinions (knowledge distribution), while what they actually output at deployment is governed by their log-probability distribution (behavior distribution). We find that when prompting LLMs to predict the opinion of a specific group, the most likely answer under the verbalized distribution differs from that under the log-probability distribution for 37% of World Values Survey questions, averaged over three LLMs. Thus, LLMs' knowledge does not match their behavior. This matters for evaluation: a verbalized distribution can score well against a group while its most likely answer is one the model never outputs, so the score no longer describes the model. The alignment scores for these two distributions reflect only the model's behavior or its knowledge, separately. We therefore propose a learnable combination of the two distributions that follows the most likely answer of the behavior distribution while preserving the shape of the knowledge distribution, with a single hyperparameter trading off behavioral fidelity against distribution quality. Our experiments on three opinion survey datasets and six models show that the balanced distribution improves behavioral consistency over the verbalized distribution from 71.6% to 95.6% on average, while the total variation distance to the human opinion distributions rises only slightly from 28.8% to 33.8%, and it remains effective under temperature scaling and cross-dataset settings.

Tue 20 OctComputation and Language
The gist
Large language models (LLMs) sometimes say different things than the knowledge they have about people’s opinions. The authors show that the answers LLMs most often produce don’t always match what the models ‘know’ about public opinion. They suggest a new method that mixes the model’s output choices with its knowledge to make answers more consistent while still reflecting real opinions. This approach makes the models’ behavior better align with what they understand about group opinions.
Open → 2610.27648v1