Progresses have been made on understanding emotion mechanisms of large language models (LLMs). However, how to explain emotion in LLMs, or even what constitutes good explanations, are less clear. Emotion representations, components, circuits are widely recoverable, but as explanations of a model's own computation they are circular; the emotion space dimensions tend to be arbitrary and non-terminating. A pressing question to ask is whether a more primitive set of internal variables does the work: the semantic primes of the Natural Semantic Metalanguage (NSM). Across four instruction-tuned LLMs (Llama-1B, Gemma-2B, Gemma-9B, OLMo-7B), experiments show that the NSM primes are (1) recoverable internal elements; and (2) on the reference model, intervening with a prime based direction controls emotion about three times as strongly, and twice as selectively, as the best appraisal based direction; and (3) the model treats a prime based explication as interchangeable with the corresponding emotion. These evidences suggest that NSM primes seem to be better explanans for emotion in LLMs than many alternative options according to scientific explanations criteria.
Why what is really a matter of data analytics and statistical prediction is so readily assumed to be a display of real intelligence and even emergent cognition is explored by genealogically tracing the relationship between machines, organisms and language.
Chantelle Gray· Deleuze and Guattari Studies· 0 citations
Different capacities for mentalization across LLMs are demonstrated, and cognitive computational modeling is highlighted as a formal method for assessing comparative intelligence across humans and machines.
Aamir Sohail, Xintong Zhong, Arkady Konovalov et al.· 0 citations
This dissertation develops a constructionist account of emotion within the predictive processing framework. It argues that emotions are not the outputs of dedicated mechanisms, but are conceptually mediated forms of predictive inference. On this view, emotion concepts are understood as hierarchically organized generative models that guide the interpretation of bodily and environmental signals, structure patterns of regulation, and coordinate action. The dissertation advances this account in three ways. First, it argues that emotions represent organism–environment relations in an evaluative sense, capturing how situations matter for the organism's ongoing activity. Second, it develops an account of anxiety as a form of stalled inference under conditions of unresolved uncertainty, explaining its anticipatory and persistent character. Third, it shows that emotions can be attributed to nonhuman animals without requiring human-level conceptual sophistication, by understanding emotion concepts as embodied and graded predictive models. Taken together, the dissertation provides a unified account of emotion as part of a predictive, conceptually structured system that enables organisms to navigate a complex and uncertain world.
It is found that while all models show sensitivity to existential presupposition across syntactic embeddings, determiner types and contextual cues, their behaviour differs markedly in strength and systematicity, with NLI-fine-tuned autoregressive models exhibiting the most coherent and stable projection patterns.
Marie-Léontine Wörgötter, Shiyang Lai, Sebastian Schuster· International Conference on...· 0 citations
The central contributions of this paper articulate the conditions under which distributional predictability threatens the internal validity of an experiment and provide concrete recommendations for how to control for this potential confound.
Sean Trott, James A. Michaelov, Cameron R. Jones et al.· Open Mind· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
