RISE is an inference-time semantic reranking framework that refines low-confidence predictions in rhetorical role labeling using contrastively learned label representations, delivering an average +9.15 macro-F1 gain on hard examples across eight datasets and seven models.
Speculative rag: Enhancing retrieval augmented generation through drafting
9 Pith papers cite this work, alongside 7 external citations. Polarity classification is still indexing.
9
Pith papers citing it
7
external citations · external index
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 9roles
background 2polarities
background 2representative citing papers
FLOWREADER reframes multimodal long-document evidence assembly as min-cost flow optimization and reports competitive results on VisDoMBench subsets with fragmented evidence.
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
Reasoning in large output spaces proceeds via shortlisting then fine-grained reasoning; this characterization enables a mechanistic distillation strategy that outperforms standard distillation.
SpecHop accelerates multi-hop LLM tool use via continuous multi-threaded speculation with asynchronous verification, approaching oracle latency gains and reducing latency up to 40% on retrieval tasks.
VArify introduces a tree visualization to support human verification of GraphRAG evidence for LLM responses in food science, evaluated in a study with six domain experts.
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.
A survey on LLM-as-a-Judge that reviews reliability strategies, proposes evaluation methods, and introduces a novel benchmark for assessing such systems.
MODE-RAG introduces a VFE-driven multi-agent pipeline with MCTS and logit perturbations to lower hallucination and sycophancy rates in multimodal RAG, tested on the new ModeVent subset of MultiVent.
citing papers explorer
-
Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling
RISE is an inference-time semantic reranking framework that refines low-confidence predictions in rhetorical role labeling using contrastively learned label representations, delivering an average +9.15 macro-F1 gain on hard examples across eight datasets and seven models.
-
FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&A
FLOWREADER reframes multimodal long-document evidence assembly as min-cost flow optimization and reports competitive results on VisDoMBench subsets with fragmented evidence.
-
Supervising the search process produces reliable and generalizable information-seeking agents
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
-
Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces
Reasoning in large output spaces proceeds via shortlisting then fine-grained reasoning; this characterization enables a mechanistic distillation strategy that outperforms standard distillation.
-
SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents
SpecHop accelerates multi-hop LLM tool use via continuous multi-threaded speculation with asynchronous verification, approaching oracle latency gains and reducing latency up to 40% on retrieval tasks.
-
VArify: A Visual Analytics System for Verifying Knowledge Enhanced Large Language Model Responses in Food Science
VArify introduces a tree visualization to support human verification of GraphRAG evidence for LLM responses in food science, evaluated in a study with six domain experts.
-
LLM-Oriented Information Retrieval: A Denoising-First Perspective
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.
-
A Survey on LLM-as-a-Judge
A survey on LLM-as-a-Judge that reviews reliability strategies, proposes evaluation methods, and introduces a novel benchmark for assessing such systems.
-
MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation
MODE-RAG introduces a VFE-driven multi-agent pipeline with MCTS and logit perturbations to lower hallucination and sycophancy rates in multimodal RAG, tested on the new ModeVent subset of MultiVent.