large language models

Digital technology risk exposure and corporate key core technology innovation

This study investigates the impact of digital technology risk exposure (DTRE) on corporate key core technology innovation (KCTI), and reveals that DTRE acts as a strategic threat, bringing about external information environment deterioration and industry‑research collaboration blockage mechanisms.

ChemE-MTDS:Multi-Turn Dialogue Data Synthesis and Quality-Controlled Fine-Tuning for Chemical Engineering Large Language Models

Formalization Matters: Conceptual Modeling with Large Language Models in High, Semi and Low-Formal Tasks

XANES_AI

Research software for XANES chemical-state interpretation in which deterministic code performs normalisation, feature extraction and peak decomposition, a large language model interprets the results, and retrieval-augmented generation supplies inspectable passages from XANES literature. The release includes the evaluat...

Controlled knowledge updating in memory-enabled AI agents: beyond model editing and recall

Large language model agents that persist across sessions, tools, users, and changing environments do more than answer isolated prompts; they accumulate state. When new evidence arrives, the central question is where that change should live: transient context, external memory, tool or workflow definitions, activation st...

Empirical Analysis of Goal Hijacking in Large Vision-Language Models via Visual Prompt Injection

In this study, we explore visual prompt injection (VPI), a method that exploits the ability of large vision-language models (LVLMs) to follow instructions embedded within input images. LVLMs, such as GPT-4V, are designed to interpret and respond to visual prompts. Although this capability enables valuable applications,...

XANES_AI

Research software for XANES chemical-state interpretation in which deterministic code performs normalisation, feature extraction and peak decomposition, a large language model interprets the results, and retrieval-augmented generation supplies inspectable passages from XANES literature. The release includes the evaluat...

Dynamic risk budgeting via large language models: A context-aware framework for adaptive portfolio allocation

Jev earnings-call pre-registration

Purpose Large language models are increasingly used to read corporate disclosures, and several studies report that an LLM's reading of earnings-call text predicts subsequent stock returns. Most of these studies date the text at the call itself, although transcripts become machine-readable only later, and they cannot ru...

Vision-Language Model-Based Demonstrators for Imitation Learning in Construction Robotic Timber Assembly

Abstract Intelligent construction robots are deemed the future of on-site construction for improved productivity and safety. To automate the construction process, imitation learning (IL) has been adopted to train construction robots in a repertoire of tasks. However, collecting demonstrations for robots to imitate from...

COLD READ: The Anonymity Half-Life Is a Property of the Reader

How many words can you write before a language model can infer who you are? This work went looking for that number and found that the question is malformed, which is itself the finding. 72 authors from the Blog Authorship Corpus, balanced across three age bands and both genders, were shown to local language models in g...

The Universal Algorithm: Physics Walls, Collective Solutions, and the Architecture of Complexity

The Universal Algorithm Physics Walls, Collective Solutions, and the Architecture of Complexity The Universal Algorithm is the general-audience synthesis of a developing research programme at the intersection of complexity science, evolutionary theory and artificial life. The programme asks whether major evolutionary t...