Local-to-Global Sentence-Level Graph Reranking for Scientific Synthesis

• URL: http://arxiv.org/abs/2608.30525v2
• Date: Mon, 07 Sep 2026 09:16:21 GMT
• Title: Local-to-Global Sentence-Level Graph Reranking for Scientific Synthesis
• Abstract summary: LoG-Reranker is a local-to-global sentence-level graph reranking framework for scientific synthesis.<n>LoG-Reranker consistently outperforms competitive rerankers.
• Score: 12.614492516746168
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-augmented scientific synthesis aims to answer complex research questions by integrating information from multiple papers into comprehensive and well-grounded responses. Since the generator can only synthesize the information selected and organized by the reranker, the quality of the generated synthesis depends critically on the reranked results. However, most rerankers operate at the passage level, which leaves key methodological, empirical, and comparative information buried in long and flat contexts, weakening the grounding of generated claims. Moreover, existing rerankers mainly rely on independent query-candidate scoring which overlooks complementary, contextual, and contrasting relations across scientific candidates, limiting information coverage and the comprehensiveness of the resulting synthesis. To address these limitations, we propose LoG-Reranker, a local-to-global sentence-level graph reranking framework for scientific synthesis. LoG-Reranker performs role-aware local scoring to identify fine-grained, query-relevant sentences and then models their relations on a sentence graph across the candidate set to globally refine sentence rankings. Top-ranked sentences and their connected neighbors are organized into a structured input context for generator to produce more grounded and comprehensive synthesis. Extensive experiments on scientific synthesis and reranking benchmarks show that LoG-Reranker consistently outperforms competitive rerankers, yielding more reliable rankings and improving the quality of generated synthesis.

Related papers

• DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
  We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
  arXiv  Detail & Related papers  (2026-01-07T03:07:52Z)
• SciRAG: Adaptive, Citation-Aware, and Outline-Guided Retrieval and Synthesis for Scientific Literature [52.36039386997026]
  We introduce SciRAG, an open-source framework for scientific literature exploration.<n>We introduce three key innovations: (1) adaptive retrieval that flexibly alternates between sequential and parallel evidence gathering; (2) citation-aware symbolic reasoning that leverages citation graphs to organize and filter documents; and (3) outline-guided synthesis that plans, critiques, and refines answers to ensure coherence and transparent attribution.
  arXiv  Detail & Related papers  (2025-11-18T11:09:19Z)
• Adapting Web Agents with Synthetic Supervision [80.89365133130558]
  Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations.<n>Recent works have explored synthetic data generation to address this challenge.<n>We propose SynthAgent, a fully synthetic supervision framework.
  arXiv  Detail & Related papers  (2025-11-08T18:45:33Z)
• Understanding the Influence of Synthetic Data for Text Embedders [52.04771455432998]
  We first reproduce and publicly release the synthetic data proposed by Wang et al.<n>We critically examine where exactly synthetic data improves model generalization.<n>Our findings highlight the limitations of current synthetic data approaches for building general-purpose embedders.
  arXiv  Detail & Related papers  (2025-09-07T19:28:52Z)
• Retro-Rank-In: A Ranking-Based Approach for Inorganic Materials Synthesis Planning [1.3676986541298586]
  Retrosynthesis strategically plans the synthesis of a chemical target compound from simpler, readily available precursor compounds.<n>We propose Retro-Rank-In, a novel framework that reformulates the retrosynthesis problem by embedding target and precursor materials into a shared latent space.<n>We show that Retro-Rank-In sets a new state-of-the-art, particularly in out-of-distribution generalization and candidate set ranking.
  arXiv  Detail & Related papers  (2025-02-06T18:34:37Z)
• SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation [55.2480439325792]
  We study the synthesis of six datasets, covering topic classification, sentiment analysis, tone detection, and humor. We find that SynthesizRR greatly improves lexical and semantic diversity, similarity to human-written text, and distillation performance.
  arXiv  Detail & Related papers  (2024-05-16T12:22:41Z)
• FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning [58.47265392465442]
  Retrosynthetic planning aims to devise a complete multi-step synthetic route from starting materials to a target molecule. Current strategies use a decoupled approach of single-step retrosynthesis models and search algorithms. We propose a novel framework that utilizes context information for improved retrosynthetic planning.
  arXiv  Detail & Related papers  (2022-09-30T08:44:58Z)
• Retroformer: Pushing the Limits of Interpretable End-to-end Retrosynthesis Transformer [15.722719721123054]
  Retrosynthesis prediction is one of the fundamental challenges in organic synthesis. We propose Retroformer, a novel Transformer-based architecture for retrosynthesis prediction. Retroformer reaches the new state-of-the-art accuracy for the end-to-end template-free retrosynthesis.
  arXiv  Detail & Related papers  (2022-01-29T02:03:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.