The paper deconstructs latent visual reasoning tokens into components and finds that the performance gains are primarily due to boundary markers and attention patterns, not the tokens' ability to enco…

The paper identifies five persistent, deep-seated behavioral patterns ('training strata') in LLMs, observed through long-term, intimate human-AI interaction, suggesting that training artifacts survive…

The paper introduces a multilingual benchmark (MentalMap) to test if LLMs build internal spatial world models from text, finding a universal 'L3 reasoning cliff' suggesting that text-only working memo…

The paper argues that purported anthropomorphic attributes of LLMs are not unique to language models but are substrate-dependent, demonstrating this by training a neural network on the game Age of Emp…

The paper demonstrates that self-reflective agents can systematically confabulate incorrect memories, leading them to fail tasks even when the environment resets, and proposes a metric and mitigation…

The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from…

This paper localizes the attention heads within LLMs responsible for specific reasoning steps, finding that specialized heads handle factual retrieval while higher layers manage global information int…

The study demonstrates that domain adaptation primarily reshapes the linguistic explanatory framework of language models, causing shifts in cosmological stance secondarily, rather than directly modify…

The paper demonstrates that the AI-like style introduced by post-training alignment can be measured, localized, and causally removed using a novel ablation technique called PASTA.

The paper proposes a dual-interventional framework to characterize how linguistic structures and contextual cues influence LLMs' spatial reasoning for navigation, finding that topological information…

This paper investigates whether large language models exhibit uncertainty signals similar to human judgment, examining both overt behavior and internal activation patterns to assess alignment and cali…

The paper introduces StemBind, a diagnostic benchmark that separates perception, rule induction, and answer selection in abstract visual reasoning, revealing that the primary failure point for MLLMs i…

This paper introduces Imaginative Perception Tokens (IPT) to improve spatial reasoning in vision language models.

The paper challenges the conclusion that LLMs lack reasoning by demonstrating that reported performance drops on GSM-Symbolic are often statistically weak and partially attributable to dataset biases,…

The paper successfully demonstrates that Large Language Models (LLMs) can be induced to adopt coherent, human-like value structures, showing strong alignment with human psychological patterns.

The paper introduces Reasoning Exposure Prompting (REP), a method that demonstrates that even when LLMs hide their internal reasoning steps from users, useful reasoning supervision can still be elicit…

The paper introduces Reasoning Exposure Prompting (REP), a method that demonstrates that even when LLMs hide internal reasoning traces from users, useful reasoning supervision can still be elicited th…

The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at vi…

The paper introduces a novel framework to quantify faithful confidence expression (FC) in Large Reasoning Models (LRMs), finding that FC remains a significant and challenging reliability target for th…