DualEnd enables whole-pool setwise reranking of 100 candidates using 50 serial LLM calls by simultaneously selecting top and bottom passages with long-context models.
hub
Rankvicuna: Zero-shot listwise doc- ument reranking with open-source large language models
23 Pith papers cite this work, alongside 11 external citations. Polarity classification is still indexing.
23
Pith papers citing it
11
external citations · Pith
abstract
Researchers have successfully applied large language models (LLMs) such as ChatGPT to reranking in an information retrieval context, but to date, such work has mostly been built on proprietary models hidden behind opaque API endpoints. This approach yields experimental results that are not reproducible and non-deterministic, threatening the veracity of outcomes that build on such shaky foundations. To address this significant shortcoming, we present RankVicuna, the first fully open-source LLM capable of performing high-quality listwise reranking in a zero-shot setting. Experimental results on the TREC 2019 and 2020 Deep Learning Tracks show that we can achieve effectiveness comparable to zero-shot reranking with GPT-3.5 with a much smaller 7B parameter model, although our effectiveness remains slightly behind reranking with GPT-4. We hope our work provides the foundation for future research on reranking with modern LLMs. All the code necessary to reproduce our results is available at https://github.com/castorini/rank_llm.
hub tools
citation-role summary
background 2
baseline 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
ZipRerank delivers state-of-the-art multimodal listwise reranking accuracy for long documents at up to 10x lower latency via early interaction and single-pass scoring.
SIGMA-ASL is a multimodal dataset with 93,545 word-level ASL clips from Kinect RGB-D, mmWave radar, and dual IMUs, plus benchmarking protocols for single- and multi-modal recognition.
Prism-Reranker models output relevance, contribution statements, and evidence passages to support agentic retrieval beyond scalar scoring.
ResRank unifies retrieval and listwise reranking by compressing passages to one token each, using residual connections and cosine-similarity scoring, achieving competitive effectiveness on TREC DL and BEIR benchmarks with zero generated tokens.
Radix-trie experiment plans in PyTerrier eliminate redundant shared-prefix computation and reduce comparative IR experiment runtime by 26% on MSMARCO v2.
KaLM-Reranker-V1 uses encoder–decoder FBNL with Matryoshka pooling to match Qwen3-class reranking quality at substantially lower online cost.
Graph-GRPO builds a dependency graph over CoT steps and propagates outcome rewards to enable finer credit assignment in generative relevance modeling for e-commerce search.
Verbal-R3 uses a verbal reranker to generate analytic narratives that guide retrieval and reasoning in LLMs, achieving SOTA results on complex QA benchmarks.
Entity-oriented rerankers show large gains in conditional evaluation but not open-world evaluation on Robust04; the paper attributes this to a coverage–discrimination tradeoff in the entity channel, not to model architecture.
Internal attention in LLMs shows a bell-curve relevance distribution across layers, enabling Selective-ICR that cuts inference latency 30-50% and lets an 8B zero-shot model match 14B RL re-rankers on BRIGHT.
Introduces the LLM ORDER BY semantic operator with algorithmic improvements, a semantic-aware external merge sort, and a budget-aware optimizer that selects near-optimal access paths for LLM-based ordering.
RankZephyr is a new open-source LLM that closes the effectiveness gap with GPT-4 for zero-shot listwise reranking while showing robustness to input ordering and document count.
LRanker combines K-means candidate aggregation with graph-partitioned ensemble of query embeddings to improve LLM ranking accuracy and scalability on massive candidate pools, reporting 3-30% gains on RBench tasks up to 6.8M candidates.
Ocean4Rec uses offline LLM to create OCEAN profiles for items and time-decayed user profiles for request-time numeric reranking, improving NDCG@20 by 7.6% and 61.5% over base+recency in offline VOD evaluations.
SCI-Defense combines perplexity detection, semantic integrity scoring across four manipulation dimensions, and inter-candidate detection to counter GEO attacks, reporting perfect precision on Amazon product data but domain-limited recall on web passages.
LLM-built attribute graphs enable zero-shot entity ranking in e-commerce with over 5% average precision gains and 57% less token usage per product compared to raw-text baselines.
AdaRankLLM shows adaptive listwise reranking outperforms fixed-depth retrieval for most LLMs by acting as a noise filter for weak models and an efficiency optimizer for strong ones, with lower context use.
LLM-generated reference documents serve as relevance pivots for dynamic ranked-list truncation and adaptive/parallel listwise reranking, reportedly beating prior RLT methods and cutting LLM reranking cost by up to 66%.
A 4B-model cascade for Thai KOL matching reaches 94.1% P@5 on 11 queries, matching a frontier model, with pairwise SimPO training transferring end-to-end while pointwise SFT+GRPO does not.
Qwen3 Embedding models in 0.6B-8B sizes achieve state-of-the-art results on MTEB and retrieval tasks including code, cross-lingual, and multilingual retrieval through unsupervised pre-training, supervised fine-tuning, and model merging on Qwen3 backbones.
citing papers explorer
-
Whole-Pool Setwise Reranking with Long-Context Language Models
DualEnd enables whole-pool setwise reranking of 100 candidates using 50 serial LLM calls by simultaneously selecting top and bottom passages with long-context models.
-
Test-Time Training for Zero-Resource Dense Retrieval Reranking
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 for Efficient Document Reranking
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
-
Very Efficient Listwise Multimodal Reranking for Long Documents
ZipRerank delivers state-of-the-art multimodal listwise reranking accuracy for long documents at up to 10x lower latency via early interaction and single-pass scoring.
-
SIGMA-ASL: Sensor-Integrated Multimodal Dataset for Sign Language Recognition
SIGMA-ASL is a multimodal dataset with 93,545 word-level ASL clips from Kinect RGB-D, mmWave radar, and dual IMUs, plus benchmarking protocols for single- and multi-modal recognition.
-
Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval
Prism-Reranker models output relevance, contribution statements, and evidence passages to support agentic retrieval beyond scalar scoring.
-
ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression
ResRank unifies retrieval and listwise reranking by compressing passages to one token each, using residual connections and cosine-similarity scoring, achieving competitive effectiveness on TREC DL and BEIR benchmarks with zero generated tokens.
-
Trie-based Experiment Plans for Efficient IR Pipeline Experiments
Radix-trie experiment plans in PyTerrier eliminate redundant shared-prefix computation and reduce comparative IR experiment runtime by 26% on MSMARCO v2.
-
KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking
KaLM-Reranker-V1 uses encoder–decoder FBNL with Matryoshka pooling to match Qwen3-class reranking quality at substantially lower online cost.
-
Graph-GRPO: Dependency-Aware Credit Assignment for Generative E-commerce Search Relevance
Graph-GRPO builds a dependency graph over CoT steps and propagates outcome rewards to enable finer credit assignment in generative relevance modeling for e-commerce search.
-
Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
Verbal-R3 uses a verbal reranker to generate analytic narratives that guide retrieval and reasoning in LLMs, achieving SOTA results on complex QA benchmarks.
-
Entities as Retrieval Signals: A Systematic Study of Coverage, Supervision, and Evaluation in Entity-Oriented Ranking
Entity-oriented rerankers show large gains in conditional evaluation but not open-world evaluation on Robust04; the paper attributes this to a coverage–discrimination tradeoff in the entity channel, not to model architecture.
-
Where Relevance Emerges: A Layer-Wise Study of Internal Attention for Zero-Shot Re-Ranking
Internal attention in LLMs shows a bell-curve relevance distribution across layers, enabling Selective-ICR that cuts inference latency 30-50% and lets an 8B zero-shot model match 14B RL re-rankers on BRIGHT.
-
Access Paths for Efficient Ordering with Large Language Models
Introduces the LLM ORDER BY semantic operator with algorithmic improvements, a semantic-aware external merge sort, and a budget-aware optimizer that selects near-optimal access paths for LLM-based ordering.
-
RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!
RankZephyr is a new open-source LLM that closes the effectiveness gap with GPT-4 for zero-shot listwise reranking while showing robustness to input ordering and document count.
-
LRanker: LLM Ranker for Massive Candidates
LRanker combines K-means candidate aggregation with graph-partitioned ensemble of query embeddings to improve LLM ranking accuracy and scalability on massive candidate pools, reporting 3-30% gains on RBench tasks up to 6.8M candidates.
-
Ocean4Rec: Offline LLM-Derived OCEAN Profiles for Request-Time VOD Reranking
Ocean4Rec uses offline LLM to create OCEAN profiles for items and time-decayed user profiles for request-time numeric reranking, improving NDCG@20 by 7.6% and 61.5% over base+recency in offline VOD evaluations.
-
SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization
SCI-Defense combines perplexity detection, semantic integrity scoring across four manipulation dimensions, and inter-candidate detection to counter GEO attacks, reporting perfect precision on Amazon product data but domain-limited recall on web passages.
-
From Unstructured to Structured: LLM-Guided Attribute Graphs for Entity Search and Ranking
LLM-built attribute graphs enable zero-shot entity ranking in e-commerce with over 5% average precision gains and 57% less token usage per product compared to raw-text baselines.
-
Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking
AdaRankLLM shows adaptive listwise reranking outperforms fixed-depth retrieval for most LLMs by acting as a noise filter for weak models and an efficiency optimizer for strong ones, with lower context use.
-
Dynamic Ranked List Truncation for Reranking Pipelines via LLM-generated Reference-Documents
LLM-generated reference documents serve as relevance pivots for dynamic ranked-list truncation and adaptive/parallel listwise reranking, reportedly beating prior RLT methods and cutting LLM reranking cost by up to 66%.
-
InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost
A 4B-model cascade for Thai KOL matching reaches 94.1% P@5 on 11 queries, matching a frontier model, with pairwise SimPO training transferring end-to-end while pointwise SFT+GRPO does not.
-
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Qwen3 Embedding models in 0.6B-8B sizes achieve state-of-the-art results on MTEB and retrieval tasks including code, cross-lingual, and multilingual retrieval through unsupervised pre-training, supervised fine-tuning, and model merging on Qwen3 backbones.