arXiv AI
Aug 10
Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding
arXiv:2608. 07353v1 Announce Type: cross Abstract: Understanding concepts is fundamental to generalization.
Comparing Semantic Navigation in Humans and Large Language Models using Natural Language Processing
arXiv:2607. 12195v1 Announce Type: cross Abstract: Semantic memory retrieval can be conceptualized as navigation through conceptual space.
Related stories
arXiv AI
Jun 3
RGMem: Renormalization Group-inspired Memory Evolution for Language Agents
arXiv:2510. 16392v3 Announce Type: replace Abstract: Personalized and continuous interactions are critical for LLM-based conversational agents, yet finite context windows and static parametric memory hinder the modeling of long-term, cross-session user states.
arXiv AI
Jun 11
The Dynamics of Human and AI-Generated Language: How Semantics Fluctuates across Different Timescales
arXiv:2606. 11371v1 Announce Type: cross Abstract: Spoken language, whether produced by humans or large language models (LLM), unfolds over time with varying semantic content.
arXiv AI
Jul 24
Response drift across frontier large language models
arXiv:2607. 20454v1 Announce Type: cross Abstract: All frontier large language models (LLMs) exhibit response drift -- producing outputs that deviate from expert-validated references -- yet the magnitude and structure of this drift remain uncharacterised by systematic human evaluation.
arXiv AI
Jun 4
Geometry-Aware Hallucination Detection in Large Language Models
arXiv:2601. 06196v3 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate factually incorrect or unsupported content, commonly referred to as hallucinations.
arXiv AI
Jun 2
MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
arXiv:2606. 01060v1 Announce Type: cross Abstract: Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally.
arXiv AI
1d ago
Automatic or Controlled? Repetition Priming Reveals Divergent Processing in Base LLMs, Instruct LLMs, and Humans
arXiv:2608. 14681v1 Announce Type: cross Abstract: Words recur constantly in natural language use, yet it remains unclear whether language models reactivate prior representations or re-evaluate repeated words afresh, and whether post-training changes this default behavior.
arXiv AI
Jul 28
Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models
arXiv:2607. 22575v1 Announce Type: new Abstract: Human episodic memory supports the retrieval of experiences that unfold over extended timescales, yet the computational mechanisms underlying this ability remain debated due to the limited mechanistic accessibility in long-term memory experiments in humans.
arXiv AI
Aug 7
Layer-wise Positional Bias in Short-Context Language Modeling
arXiv:2601. 04098v2 Announce Type: replace-cross Abstract: Transformer language models systematically prefer tokens at specific input positions regardless of semantic relevance---a phenomenon known as positional bias.
arXiv AI
Jun 3
Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models
arXiv:2606. 03165v1 Announce Type: cross Abstract: The language used by digital chat assistants such as ChatGPT can diverge from human expectations (misalignment).
arXiv AI
Aug 6
MemFly: On-the-Fly Memory Optimization via Information Bottleneck
arXiv:2602. 07885v2 Announce Type: replace Abstract: Long-term memory enables large language model agents to tackle complex tasks through historical interactions.
arXiv AI
Jul 7
Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision
arXiv:2605. 28865v2 Announce Type: replace-cross Abstract: What does a world model learn from physical exploration, without any linguistic supervision?