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 Canonical reference
Yao Meng, Chenyan Xiong, Zhenghao Liu, Zhiyuan Liu, and Jiawei Han
Canonical reference. 80% of citing Pith papers cite this work as background.
22
Pith papers citing it
20
external citations · external index
Background
80% of classified citations
hub tools
citation-role summary
background 3
method 2
citation-polarity summary
representative citing papers
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
On-policy distillation has an extrapolation cliff at closed-form lambda*(p,b,c) set by teacher modal probability, warm-start mass, and clip strength, past which training shifts from format-preserving to format-collapsing.
InvariRank achieves permutation-invariant listwise reranking for LLM-based recommendations via a structured attention mask that blocks cross-candidate interactions and shared positional framing under RoPE, enabling stable rankings in one forward pass.
HeadRank lifts preference optimization into attention space via entropy-regularized head selection and distribution regularizers to sharpen discriminability for efficient listwise reranking.
Agentic search over NASA EO-KG yields a 47k-pair benchmark where neural scoring plus LLM reranking raises MRR by over 5x then an additional 28%.
A single LLM trained to emit semantic item codes can fulfill complex shopping intents with fewer tool hand-offs, improving multi-turn follow-up on Taobao-derived tasks.
Verbal-R3 uses a verbal reranker to generate analytic narratives that guide retrieval and reasoning in LLMs, achieving SOTA results on complex QA benchmarks.
RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document 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.
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.
ProRank uses RL-based prompt warmup and fine-grained scoring to train small language models that surpass LLM rerankers on BEIR.
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.
Gradient-based and instruction-override prompt injections largely fail to survive retrieval and reranking in realistic RAG systems, while only LLM-driven injections remain effective end-to-end, and all attacks are detectable by a lightweight guard.
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.
GroupRank uses groupwise LLM reranking with answer-free data synthesis and a group-ranking reward to reach 65.2 NDCG@10 on BRIGHT while providing 6.4x faster inference than listwise baselines.
Wrapping LLM calls as oracles in classical algorithms improves sorting and clustering accuracy for small models, but several advertised applications are missing from the experiments.
LLM-generated synthetic hard negatives for training dense retrievers consistently underperform corpus-mined negatives from BM25 and cross-encoders across 10 BEIR datasets, with non-monotonic gains from scaling the generator from 4B to 30B parameters.
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.
5ting achieves nDCG@5 of 0.4719 on Task A and harmonic score 0.5597 with RL_F 0.7692 on Task C for multi-turn RAG via standard dense retrieval plus LLM reranking and faithfulness constraints.
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.
-
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
-
The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs
On-policy distillation has an extrapolation cliff at closed-form lambda*(p,b,c) set by teacher modal probability, warm-start mass, and clip strength, past which training shifts from format-preserving to format-collapsing.
-
One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation
InvariRank achieves permutation-invariant listwise reranking for LLM-based recommendations via a structured attention mask that blocks cross-candidate interactions and shared positional framing under RoPE, enabling stable rankings in one forward pass.
-
HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads
HeadRank lifts preference optimization into attention space via entropy-regularized head selection and distribution regularizers to sharpen discriminability for efficient listwise reranking.
-
Bringing Agentic Search to Earth Observation Data Discovery
Agentic search over NASA EO-KG yields a 47k-pair benchmark where neural scoring plus LLM reranking raises MRR by over 5x then an additional 28%.
-
ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping
A single LLM trained to emit semantic item codes can fulfill complex shopping intents with fewer tool hand-offs, improving multi-turn follow-up on Taobao-derived tasks.
-
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.
-
Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.
-
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.
-
ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking
ProRank uses RL-based prompt warmup and fine-grained scoring to train small language models that surpass LLM rerankers on BEIR.
-
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.
-
Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings
Gradient-based and instruction-override prompt injections largely fail to survive retrieval and reranking in realistic RAG systems, while only LLM-driven injections remain effective end-to-end, and all attacks are detectable by a lightweight guard.
-
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.
-
GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs
GroupRank uses groupwise LLM reranking with answer-free data synthesis and a group-ranking reward to reach 65.2 NDCG@10 on BRIGHT while providing 6.4x faster inference than listwise baselines.
-
Verbalized Algorithms: Classical Algorithms are All You Need (Mostly)
Wrapping LLM calls as oracles in classical algorithms improves sorting and clustering accuracy for small models, but several advertised applications are missing from the experiments.
-
Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval
LLM-generated synthetic hard negatives for training dense retrievers consistently underperform corpus-mined negatives from BM25 and cross-encoders across 10 BEIR datasets, with non-monotonic gains from scaling the generator from 4B to 30B parameters.
-
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.
-
5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control
5ting achieves nDCG@5 of 0.4719 on Task A and harmonic score 0.5597 with RL_F 0.7692 on Task C for multi-turn RAG via standard dense retrieval plus LLM reranking and faithfulness constraints.