The paper investigates whether modestly sized open-source language models can grasp the semantics of rare Paired-Focus constructions, finding that understanding emerges later in training and correlate…

AnyEdit++ introduces a structure-aware framework that uses Bayesian Surprise to adaptively segment long-form knowledge, significantly improving the coherence and accuracy of knowledge editing in LLMs.

The paper systematically compares multiple content representations for RAG pipelines and finds that answer retention—the ability of the representation to preserve the original answer-bearing content—i…

This paper proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…

The paper introduces Semantic Triplet Restoration (STR), a novel protocol that converts complex table structures into atomic semantic triplets, improving table question answering by providing explicit…

This paper analyzes the multilinguality of LLMs by examining their structural properties, finding that low-resource languages are structurally more distinct from English than high-resource languages,…

This paper investigates whether a group of people highlighting the same document forms a single consensus or is internally structured into reader sub-groups.

The paper investigates compositional abilities in LLMs and humans using the Personal Relation Task, finding that LLMs excel at the structured (Intensional) task while humans are better at the real-wor…

The authors introduce Structured PubMed, a comprehensive corpus of section-labeled biomedical abstracts compiled from the complete PubMed database.

The paper introduces the Vector Network (VN), a novel recurrent architecture that replaces fixed weight matrices with reusable weight atoms, enabling superior compositional generalization by making st…

AnchorSteer introduces a framework that achieves high-fidelity, structure-preserving music editing by decoupling semantic concept injection from structural constraints.

The paper introduces ProtStructQA, an executable benchmark that tests protein structural reasoning by requiring language models to generate measurable 3D coordinates, revealing a capability-dependent…

The paper proposes MACAT, a Multi-Agent Culture-Aware Translation framework, to selectively translate culture-loaded words in ancient Chinese texts, achieving superior performance over existing method…

The paper introduces COMPOSE, a dual-graph framework that generates plausible future mathematical theorems by simultaneously conditioning a language model on both the scientific citation context and t…

The paper demonstrates that content suppression techniques used in language models only mask prohibited content at the output level, failing to eliminate the underlying concepts from the model's inter…

This study systematically evaluates a wide range of chunking methods for Retrieval-Augmented Generation (RAG) to assess their effectiveness and highlight the overlooked challenges associated with chun…

This paper demonstrates that targeted adaptation of the small language model Phi Silica, using dataset curation and fine-tuning, significantly improves its performance in short-form text rewriting, na…

The paper proposes a disentangled representation framework to significantly improve few-shot layout-to-image generation by separating semantic identity from local visual details, thereby mitigating re…

The paper proposes SubFit, a novel compression technique that achieves superior LLM compression by replacing non-contiguous, submodule-level components (Attention and FeedForward) with lightweight res…

This paper evaluates the causal reasoning abilities of large language models and finds that they rely heavily on lexical pattern matching rather than structural reasoning.