CoRRabs/2003.07820(2020), https://arxiv.org/ abs/2003.07820

representative citing papers

citing papers explorer

Showing 18 of 18 citing papers.

• Layer-wise Token Compression for Efficient Document Reranking cs.IR · 2026-05-20 · unverdicted · none · ref 10 · 2 links

  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

• Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models cs.IR · 2026-05-02 · unverdicted · none · ref 14

  CRAFT is a supervised LLM framework using retrieval-augmented generation, self-refinement, fine-tuning, and preference optimization to create fluent adversarial content that boosts target ranks in neural ranking models, outperforming baselines on MS MARCO and TREC benchmarks with cross-architecture

• ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression cs.IR · 2026-04-24 · conditional · none · ref 25

  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.

• HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads cs.IR · 2026-04-19 · unverdicted · none · ref 34

  HeadRank lifts preference optimization into attention space via entropy-regularized head selection and distribution regularizers to sharpen discriminability for efficient listwise reranking.

• Scaling Laws for Cross-Encoder Reranking cs.IR · 2026-03-05 · unverdicted · none · ref 12

  Cross-encoder reranker performance scales predictably via power laws with model size and training exposure, allowing accurate forecasts for 400M and 1B models and data-heavy compute allocation.

• GAIA: a benchmark for General AI Assistants cs.CL · 2023-11-21 · unverdicted · none · ref 89

  GAIA benchmark shows humans at 92% accuracy on simple real-world questions far outperform current AI systems at 15%, proposing this gap as a key milestone for general AI.

• RAQG-QPP: Query Performance Prediction with Retrieved Query Variants and Retrieval Augmented Query Generation cs.IR · 2026-04-29 · unverdicted · none · ref 48

  Retrieved query variants from logs combined with LLM-augmented generation improve unsupervised QPP accuracy by up to 30% for neural rankers on TREC DL'19 and DL'20.

• Data, Not Model: Explaining Bias toward LLM Texts in Neural Retrievers cs.IR · 2026-04-07 · unverdicted · none · ref 5

  Bias toward LLM texts in neural retrievers arises from artifact imbalances between positive and negative documents in training data that are absorbed during contrastive learning.

• Formalized Information Needs Improve Large-Language-Model Relevance Judgments cs.IR · 2026-04-05 · conditional · none · ref 13

  Synthetically formalizing information needs into topics with descriptions and narratives improves LLM relevance assessor agreement with humans and reduces over-labeling of relevant documents on TREC Deep Learning and Robust04.

• Where Relevance Emerges: A Layer-Wise Study of Internal Attention for Zero-Shot Re-Ranking cs.IR · 2026-02-26 · unverdicted · none · ref 4

  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 cs.DB · 2025-08-30 · unverdicted · none · ref 11

  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.

• RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models cs.IR · 2025-02-02 · unverdicted · none · ref 12

  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.

• A Reproducibility Study of LLM-Based Query Reformulation cs.IR · 2026-04-30 · unverdicted · none · ref 9

  A unified evaluation finds LLM query reformulation gains are strongly conditioned on retrieval paradigm, do not consistently transfer to neural retrievers, and are not uniformly improved by larger LLMs.

• Efficient Listwise Reranking with Compressed Document Representations cs.IR · 2026-04-29 · unverdicted · none · ref 8

  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.

• Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval cs.IR · 2026-04-06 · unverdicted · none · ref 4

  Stratified sampling preserving teacher score distribution outperforms hard-negative mining as a robust baseline for knowledge distillation in dense retrieval.

• Statistical Foundations of DIME: Risk Estimation for Practical Index Selection cs.IR · 2026-01-09 · unverdicted · none · ref 3

  A statistical risk estimation method enables query-specific dimension selection in dense embeddings, achieving equivalent effectiveness with about 50% smaller embeddings at inference time.

• Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval cs.IR · 2026-04-29 · conditional · none · ref 11

  Reproducibility study confirms Hypencoder's non-linear query-specific scoring improves retrieval over bi-encoders on standard benchmarks but standard methods remain faster and hard-task results are mixed due to implementation issues.

• Dynamic Ranked List Truncation for Reranking Pipelines via LLM-generated Reference-Documents cs.IR · 2026-04-10 · unreviewed · ref 4