Superficial Beliefs in LLM Decision-Making
We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic underlying decision structure. Using synthetic binary decision settings in which models choose between profiles defined by graded attributes, we compare the attribute a model says mattered most with the attribute that best explains its choice under a behavioural model fit to prior decisions. The behavioural model predicts held-out choices well, showing that model behaviour is systematically related to the visible attributes rather than being random. However, direct self-reports and a separate score-based judge recover the behaviourally inferred driver only partially. The resulting picture is neither one of arbitrary behaviour nor one of fully articulated belief - outputs are structured enough to support prediction, but explicit reasons track the recovered driver only imperfectly. This qualitative pattern persists across prompt-order and sampling perturbations, alternative behavioural models, targeted occlusion analyses, and structurally varied decision settings. We interpret this as evidence for ``superficial belief'' in LLM decision-making: models behave as if guided by probabilistic local priorities over attributes, while having only limited verbal access to the attributes that drive their decisions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Belief patterns with information processing
This paper presents a model of costly information acquisition where decision-makers can choose whether to elaborate information superficially or precisely. The former action is costless, while the latter entails a proces…
Bayesian InferenceDecision MakingA maximum entropy model of bounded rational decision-making with prior beliefs and market feedback
Bounded rationality is an important consideration stemming from the fact that agents often have limits on their processing abilities, making the assumption of perfect rationality inapplicable to many real tasks. We propo…
Decision MakingNormative Evaluation of Large Language Models with Everyday Moral Dilemmas
The rapid adoption of large language models (LLMs) has spurred extensive research into their encoded moral norms and decision-making processes. Much of this research relies on prompting LLMs with survey-style questions t…
Decision MakingDesign of a Framework to Facilitate Decisions Using Information Fusion
Information fusion is an advanced research area which can assist decision makers in enhancing their decisions. This paper aims at designing a new multi-layer framework that can support the process of performing decisions…
Decision MakingWhen Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMs
Large language models (LLMs) are increasingly deployed in high-stakes settings where good decisions require forming beliefs over the probability of unknown outcomes. However, it is unclear whether LLMs act as if they hol…