arXiv Computation and Language
How Does Post-Training Shape LLM Value Preferences?
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Machine Learning
Jul 16
Value Drifts: Tracing Value Alignment During LLM Post-Training
arXiv:2510. 26707v2 Announce Type: replace-cross Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to align with certain human value systems.
arXiv Computation and Language
Oct 21
Speak vs. Know: Balancing Behavior and Knowledge Distributions of Large Language Models
The paper investigates the mismatch between large language models’ verbalized (knowledge) distributions and their actual output (behavior) distributions when predicting group opinions. It shows that for 37% of World Values Survey questions, the most likely answer under the verbalized distribution differs from that under the log‑probability distribution, indicating a disconnect between what the model knows and what it outputs. To reconcile this, the authors propose a learnable combination of the two distributions that preserves the knowledge shape while aligning with the behavior’s most likely answer, achieving higher behavioral consistency with only a modest increase in distance to human opinion distributions.
arXiv Computation and Language
Sep 1
Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation
arXiv:2608.30902v1 Announce Type: new Abstract: Adapting large language models to user-specific preferences is often constrained by the cost of human annotation, making preference optimisation imprac...
arXiv Computation and Language
Sep 1
Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments
arXiv:2608.29803v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as proxies for human participants in social simulations, yet whether they update their beliefs...
arXiv Computation and Language
Oct 21
How Language Models Learn Taste: Brand Preference in LLMs
The paper investigates how large language models develop brand preferences, noting that models often name market‑leading brands like Nike when asked for a running shoe brand but recommend niche brands such as Brooks. Across 102 models and 42 brand categories, the brand chosen for recommendation differs from the named brand in 26% of cases, and preference optimization (DPO) shifts these choices by 11–24 points. The study suggests that pretraining already links recommended brands to advice, supervised fine‑tuning preserves these preferences, and DPO can shift them even when the preferred brand is absent from the preference data, indicating that the judge models used in training play a key role.
Hugging Face Trending Papers
Oct 20
How Language Models Learn Taste: Brand Preference in LLMs
Asked to name a running shoe brand, language models say Nike. Asked to recommend one, they say Brooks. This paper asks where models learn that taste. Across 102 models and 42 brand categories, the bra...