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…

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 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 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 introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that curre…

TalTech submitted top-ranking systems to the Beyond Transcription Challenge using fine-tuned Voxtral models and reinforcement learning against Open Medical Concept F1.

This paper compares three methods for answering questions over legal documents: full-corpus injection, embedding retrieval, and LLM navigation over a compact structured index. The results show that th…

LongTraceRL addresses long-context reasoning challenges by generating highly challenging training data and introducing a fine-grained rubric reward, significantly improving evidence-grounded reasoning…

The paper introduces DrugClaw, a multi-agent system, and DrugAudit, a new benchmark, demonstrating that DrugClaw excels at answering drug-related questions by grounding answers in primary regulatory s…

GrepSeek introduces a novel direct corpus interaction (DCI) search agent that trains an LLM to find and compose evidence from large text corpora by issuing executable shell commands, achieving state-o…

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.

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

The paper introduces PlanRAG, a framework for Retrieval-Augmented Generation (RAG) that models exploratory reasoning problems as logical query trees, addressing representation and optimization gaps be…

The paper introduces a typed claim network that models cross-document references by explicitly labeling the stance (e.g., agreement, disagreement) of a citation, significantly improving downstream tas…

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

This paper compares sparse and dense retrieval models for scientific claim-source retrieval on the CheckThat! 2026 benchmark. Translating claims into English and incorporating publication metadata imp…