This paper introduces KGERMAR, a framework that constructs dynamic, context-specific knowledge graphs during inference for long-context language modeling, achieving lower perplexity and better memory…

This paper proposes a post-training framework called Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT) to teach language models to reason by analogy.

The paper proposes AlignG, a method that learns context-conditioned predicate semantics by using prototype feedback to adapt relation representations based on image-specific evidence, significantly im…

This paper proposes a lightweight encoder-based MEL solution called FAST-MEL that meets three objectives: high linking accuracy, computational efficiency, and storage efficiency.

The paper introduces a distributional framework using Wasserstein distance to unify the semantic comparison of sparse autoencoder features across different layers and to automatically compress large f…

The paper proposes InSemRAG, an enhanced RAG framework that improves retrieval accuracy and knowledge integrity by incorporating intent-aware retrieval and semantics-preserving chunking, achieving sta…

This paper introduces a Hybrid Mixture-of-Experts (HybridMoE) framework and a specialized corpus (Varnika) to significantly improve language models' ability to understand and retain figurative, cultur…

EvoGens is an evolution-inspired framework that treats scientific idea generation as an evolutionary search, significantly boosting the novelty and diversity of generated research ideas compared to ex…

The paper introduces MIDI, a novel multilingual dataset that embeds idioms in realistic sentence and conversational contexts across diverse resource levels, revealing that idiom comprehension is signi…

The paper proposes a graph-constrained approach to scale multi-hop training data by decoupling path discovery from path verbalization, significantly expanding the usable corpus size for LLMs.

The paper introduces CERA, a novel contrastive retrieval framework that improves RAG factuality and interpretability by using subjectivity-based hard negative selection and an auxiliary attention alig…

The paper introduces ACROS, a method that induces an explicit sense representation pathway into a frozen pretrained decoder LM, enabling sense-based tasks like disambiguation and cross-lingual alignme…

SWAN introduces a novel, training-free framework that embeds watermarks directly into the semantic structure of a sentence using Abstract Meaning Representation (AMR), achieving superior robustness ag…

The paper introduces Rationalize, a role-pair framework that facilitates shared semantic reasoning between humans and AI models to achieve deep alignment of intent and action.

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 paper introduces 'bundesrecht,' an open-source, end-to-end pipeline for processing complex German statutory references, which parses, normalizes, and resolves raw citation strings into structured,…

The paper evaluates the semantic stability of clinical LLMs to linguistic variations, finding that domain specialization does not guarantee consistent robustness improvements.

The paper introduces a robust four-stage NLP framework that uses schema-constrained LLMs and ESCO vocabulary to accurately extract and align educational competencies with labor market demands, quantif…

The paper presents BEATS, a human-in-the-loop LLM framework for bootstrapping product attribute taxonomies from scratch.

The paper proposes UniRule, a novel agentic RAG framework that unifies the detection rule generation process by mapping context and language to rules, significantly outperforming pure LLM generation.