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.
hub
Large language models are effective text rankers with pairwise ranking prompting.arXiv preprint arXiv:2306.17563
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
abstract
Ranking documents using Large Language Models (LLMs) by directly feeding the query and candidate documents into the prompt is an interesting and practical problem. However, researchers have found it difficult to outperform fine-tuned baseline rankers on benchmark datasets. We analyze pointwise and listwise ranking prompts used by existing methods and argue that off-the-shelf LLMs do not fully understand these challenging ranking formulations. In this paper, we propose to significantly reduce the burden on LLMs by using a new technique called Pairwise Ranking Prompting (PRP). Our results are the first in the literature to achieve state-of-the-art ranking performance on standard benchmarks using moderate-sized open-sourced LLMs. On TREC-DL 2019&2020, PRP based on the Flan-UL2 model with 20B parameters performs favorably with the previous best approach in the literature, which is based on the blackbox commercial GPT-4 that has 50x (estimated) model size, while outperforming other LLM-based solutions, such as InstructGPT which has 175B parameters, by over 10% for all ranking metrics. By using the same prompt template on seven BEIR tasks, PRP outperforms supervised baselines and outperforms the blackbox commercial ChatGPT solution by 4.2% and pointwise LLM-based solutions by more than 10% on average NDCG@10. Furthermore, we propose several variants of PRP to improve efficiency and show that it is possible to achieve competitive results even with linear complexity.
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
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.
ReasonRank synthesizes reasoning-intensive training data using DeepSeek-R1 and applies a two-stage SFT plus RL process with a novel multi-view ranking reward to create a listwise reranker that outperforms baselines with lower latency than pointwise methods.
LLMs show a quality-dependent position bias, favoring the first option for high-quality choices and later options for low-quality ones, and higher-temperature sampling can reveal the underlying preference.
RankFlow deploys four LLM roles in sequence to rewrite queries, generate pseudo-answers, summarize passages, and rerank candidates, outperforming prior methods on TREC-DL, BEIR, and NovelEval.
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.
DyLAN automatically selects and dynamically organizes LLM agents for collaboration, outperforming fixed-agent baselines on code generation, reasoning, and decision tasks with up to 25% accuracy gains on some MMLU subjects.
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.
RRK compresses documents to multi-token embeddings for efficient listwise reranking, enabling an 8B model to achieve 3x-18x speedups over smaller models with comparable or better effectiveness.
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.
TSGuard builds domain knowledge bases offline from historical incidents and applies online multi-agent structured reasoning to diagnose AI workload failures, delivering 19.8% higher accuracy and 63.4% lower verification time than baselines on Azure production data.
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.
Fortress stabilizes query-to-app relevance models by pruning features that cause inconsistent predictions across time periods while retaining predictive power from engagement signals.
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.
citing papers explorer
-
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.
-
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.
-
ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability
ReasonRank synthesizes reasoning-intensive training data using DeepSeek-R1 and applies a two-stage SFT plus RL process with a novel multi-view ranking reward to create a listwise reranker that outperforms baselines with lower latency than pointwise methods.
-
Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models
LLMs show a quality-dependent position bias, favoring the first option for high-quality choices and later options for low-quality ones, and higher-temperature sampling can reveal the underlying preference.
-
RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models
RankFlow deploys four LLM roles in sequence to rewrite queries, generate pseudo-answers, summarize passages, and rerank candidates, outperforming prior methods on TREC-DL, BEIR, and NovelEval.
-
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.
-
A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
DyLAN automatically selects and dynamically organizes LLM agents for collaboration, outperforming fixed-agent baselines on code generation, reasoning, and decision tasks with up to 25% accuracy gains on some MMLU subjects.
-
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.
-
Efficient Listwise Reranking with Compressed Document Representations
RRK compresses documents to multi-token embeddings for efficient listwise reranking, enabling an 8B model to achieve 3x-18x speedups over smaller models with comparable or better effectiveness.
-
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.
-
TSGuard: Automated User-Centric Incident Diagnosis for AI Workloads in the Cloud
TSGuard builds domain knowledge bases offline from historical incidents and applies online multi-agent structured reasoning to diagnose AI workload failures, delivering 19.8% higher accuracy and 63.4% lower verification time than baselines on Azure production data.
-
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.
-
Fortress: A Case Study in Stabilizing Search Recommendations via Temporal Data Augmentation and Feature Pruning
Fortress stabilizes query-to-app relevance models by pruning features that cause inconsistent predictions across time periods while retaining predictive power from engagement signals.
-
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.