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

This paper introduces robustness indicators to systematically analyze how multilingual text embedding model rankings change based on dataset composition and aggregation methods, revealing that only a…

This paper proposes CompRank, a token-efficient reranking framework for large language models that reduces redundant computation and achieves strong reranking performance.

The paper introduces and evaluates five parameter alignment strategies that significantly mitigate catastrophic forgetting when continually pretraining multilingual expert language models across multi…

The paper introduces Single-stage Sparse Retrieval (SSR), a method that replaces computationally expensive vector clustering with sparse autoencoding to achieve highly efficient multi-vector retrieval…

The paper introduces RAG-Pref, a novel, training-free Retrieval Augmented Generation (RAG) method for preference alignment that significantly improves LLM refusal guardrails against agentic attacks wi…

The authors demonstrate that fine-tuning a two-stage retrieval system using synthetic data generated by large language models can significantly improve the performance of medical semantic search for c…

The paper introduces SPECTRA, a scalable framework for generating large, synthetic, and controllable information retrieval test collections, demonstrating its ability to expose system scaling and fail…

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 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 a diagnostic framework to decompose multilingual LLM performance variance, showing that language identity and model-benchmark interactions are key drivers of performance gaps.

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.

OmniRetrieval introduces a unified framework that handles natural language queries across diverse, heterogeneous knowledge sources (text, relational, graphs) by dispatching source-native queries witho…

The paper introduces a new benchmark for multi-target cross-lingual summarization (MTXLS) and proposes an activation steering method that significantly improves LLM performance by guiding the generati…

The paper introduces RA-MoE, a novel fine-tuning framework that leverages the internal routing structure of Mixture-of-Experts (MoE) models to improve performance on multilingual downstream tasks by a…

CoHyDE introduces an iterative co-training framework that jointly optimizes an LLM rewriter and a dense encoder, significantly improving tool retrieval accuracy for LLM agents, especially on vague que…

This study systematically analyzes strategies for creating reliable multilingual LLMs-as-a-judge, finding that fine-tuning smaller models with in-domain data is effective, while zero-shot evaluation w…