FollowTable is the first large-scale benchmark for instruction-following table retrieval, paired with an Instruction Responsiveness Score, showing that existing models fail to adapt to fine-grained constraints beyond topical similarity.
hub Mixed citations
Rank1: Test-time compute for reranking in information retrieval
Mixed citation behavior. Most common role is background (60%).
16
Pith papers citing it
Background
60% of classified citations
hub tools
citation-role summary
background 3
baseline 1
other 1
citation-polarity summary
representative citing papers
DART adapts a scoring matrix at inference time via gradient updates on pseudo-labels from top/bottom documents to gain +2.1% mean NDCG@10 on six BEIR benchmarks with under 10ms added latency.
Layer-wise Token Compression applies adaptive token pooling at middle transformer layers for cross-encoder rerankers, preserving MS MARCO ranking quality while raising QPS up to 25% on passages and 116% on documents, with added gains on listwise LLM rerankers and a regularizer effect for long inputs
LeanSearch v2 recovers 46.1% of ground-truth premise groups for research-level Lean 4 theorems within 10 candidates and raises fixed-loop proof success to 20%.
BRIGHT-Pro and RTriever-Synth advance reasoning-intensive retrieval by adding multi-aspect evidence evaluation and aspect-decomposed synthetic training, with the fine-tuned RTriever-4B showing gains over its base model.
MARVEL reaches 37.9 nDCG@10 on the MM-BRIGHT benchmark by combining LLM query expansion, a reasoning-enhanced dense retriever, and GPT-4o CoT reranking, beating prior multimodal encoders by 10.3 points.
RICE-PO is a policy optimization framework that converts retrieval interactions into credit signals for latent reasoning steps in agents by selecting high-uncertainty actions as anchors and propagating credit based on influence strength and residual stability, outperforming baselines on BRIGHT and B
Proposes PDF, a hierarchical multi-agent Perception-to-Deliberation Framework that adds experience self-evolution and test-time scaling to composed image retrieval, claiming SOTA on CIRR, CIRCO, and FashionIQ.
Verbal-R3 uses a verbal reranker to generate analytic narratives that guide retrieval and reasoning in LLMs, achieving SOTA results on complex QA benchmarks.
A survey that categorizes RIR benchmarks by domain and modality, proposes a taxonomy for integrating reasoning into retrieval pipelines, and outlines key challenges.
DualView fuses local cross-attention and global context aggregation via adaptive gating to rerank fixed candidate sets for multi-hop QA, reporting 99.4% Top-4 Recall on MuSiQue at 4 ms latency while beating larger cross-encoders.
HIVE raises multimodal retrieval nDCG@10 to 41.7 on the MM-BRIGHT benchmark by inserting LLM-driven hypothesis generation and verification between retrieval passes, delivering +9.5 over the best text-only baseline and +14.1 over the best multimodal baseline.
ProRank uses RL-based prompt warmup and fine-grained scoring to train small language models that surpass LLM rerankers on BEIR.
TTSP resolves the Grounding Paradox by treating perception as a scalable test-time process that generates, filters, and iteratively refines multiple visual exploration traces, outperforming baselines on high-resolution and multimodal reasoning tasks.
Reproducing GAR on BRIGHT shows it boosts reasoning-intensive retrieval effectiveness with low overhead when the reranker's signal quality is strong.
citing papers explorer
-
LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
LeanSearch v2 recovers 46.1% of ground-truth premise groups for research-level Lean 4 theorems within 10 candidates and raises fixed-loop proof success to 20%.