Related papers: How to Tame Your LLM: Semantic Collapse in Continu…
Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer,…
Current research on large language model (LLM) agents is fragmented: discussions of conceptual frameworks and methodological principles are frequently intertwined with low-level implementation details, causing both readers and authors to…
An introduction to the CSL (Continuous Spontaneous Localization) theory of dynamical wave function collapse is provided, including a derivation of CSL from two postulates. There follows applications to a free particle, or to a `small' rigid…
We deploy the methods of controlled psycholinguistic experimentation to shed light on the extent to which the behavior of neural network language models reflects incremental representations of syntactic state. To do so, we examine model…
One of the long-standing goals in optimisation and constraint programming is to describe a problem in natural language and automatically obtain an executable, efficient model. Large language models appear to bring this vision closer,…
Languages continually evolve in response to societal events, resulting in new terms and shifts in meanings. These changes have significant implications for computer applications, including automatic translation and chatbots, making it…
Iterative LLM systems(self-refinement, chain-of-thought, autonomous agents) are increasingly deployed, yet their temporal dynamics remain uncharacterized. Prior work evaluates task performance at convergence but ignores the trajectory: how…
Most language modeling methods rely on large-scale data to statistically learn the sequential patterns of words. In this paper, we argue that words are atomic language units but not necessarily atomic semantic units. Inspired by HowNet, we…
Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in…
Diffusion models (DMs) have achieved remarkable success across various domains owing to their strong generative and denoising capabilities. Meanwhile, semantic communication based on neural joint source-channel coding (JSCC) has emerged as…
Large language models (LLMs) have greatly improved their capability in performing NLP tasks. However, deeper semantic understanding, contextual coherence, and more subtle reasoning are still difficult to obtain. The paper discusses…
Recent work on predicting category structure with distributional models, using either static word embeddings (Heyman and Heyman, 2019) or contextualized language models (CLMs) (Misra et al., 2021), report low correlations with human…
In recent years, central components of a new approach to linguistics, the Minimalist Program (MP) have come closer to physics. Features of the Minimalist Program, such as the unconstrained nature of recursive Merge, the operation of the…
Latent diffusion models such as Stable Diffusion achieve state-of-the-art results on text-to-image generation tasks. However, the extent to which these models have a semantic understanding of the images they generate is not well understood.…
This paper presents a semantics of self-adjusting computation and proves that the semantics are correct and consistent. The semantics integrate change propagation with the classic idea of memoization to enable reuse of computations under…
Recent advances in Large Language Models (LLMs) have demonstrated the emergence of capabilities (learned skills) when the number of system parameters and the size of training data surpass certain thresholds. The exact mechanisms behind such…
Most semantic drift studies report multiple signals e.g., embedding displacement, neighbor changes, distributional divergence, and recursive trajectory instability, without a shared explanatory theory that relates them. This paper proposes…
Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional encoder-decoder policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT…
Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While this has been well investigated in Computer Vision, in…
Cognitive dynamics are pivotal to advance human understanding of the world. Recent advancements in large language models (LLMs) reveal their potential for cognitive simulation. However, these LLM-based cognitive studies primarily focus on…