The paper introduces a new term expansion for a calculus with explicit substitutions, allowing the relation of a lambda-calculus with explicit substitutions to Boudol's resource aware lambda-calculus.

The paper proposes a low-cost and interpretable fine-tuning extraction strategy for automatic term extraction, demonstrating consistent and balanced performance on the ATE Shared Task.

The paper introduces ADORE, an iterative framework for query expansion using LLMs, which turns retrieval outcomes into feedback for the next expansion.

The paper compares two families of methods for ranking case-law sentences by their usefulness for explaining statutory concepts using ModernBERT and decoder-only models. Decoder-only models achieve th…

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 proposes a method for reducing false reject rates in keyword spotting models on embedded devices with limited resources, using parameter-capped modular expansion.

This paper proposes FinSAgent, an evidence-grounded multi-agent framework for financial question answering over SEC filings, which improves retrieval coverage and answer correctness through corpus-sid…

The paper theoretically analyzes the limitations of parameter-based knowledge editing and empirically demonstrates that these methods consistently damage core LLM capabilities compared to retrieval-ba…

The paper introduces Global PSRO, a novel deep reinforcement learning framework that efficiently approximates Nash equilibria in large two-player zero-sum games by intelligently expanding the strategy…

Introduces Expanding Generative Flows (EFlows) and Expanding Flow Maps (EFMs) for generating outputs of varying sizes in continuous and discrete state spaces.

The paper introduces Latent Terms, a method that shows dense retrieval models implicitly learn sparse, Zipfian vocabularies that can be used for classical BM25-style sparse scoring without requiring s…

MolLingo is a multi-agent system that significantly improves automated molecular design by integrating domain-specific chemical reasoning and structural context into LLMs, outperforming state-of-the-a…

The paper introduces an agentic framework for text clustering that dynamically adapts the taxonomy generation process using specialized LLM agents, achieving state-of-the-art performance on multiple b…

KairosAgent is a novel agentic framework that combines Large Language Models (LLMs) for semantic reasoning and Time Series Foundation Models (TSFMs) for numerical forecasting, achieving superior multi…

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…

This paper proposes a multi-turn retrieval-augmented generation pipeline for conversational systems across four domains.

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…

This paper introduces model merging as a training-free strategy for designing a single retrieval model that operates across both ad-hoc and conversational settings, improving ad-hoc search capabilitie…

The paper proposes A2X, an LLM-native progressive-disclosure scheme that structures service taxonomies hierarchically and searches them layer-by-layer at query time, solving context overflow and impro…