Quotient DAGs enable forward-flow importance sampling and exact unordered slate propensities via Forward-DP for autoregressive slate loggers under set-sufficient interfaces.
hub
Is C hat GPT Good at Search? Investigating Large Language Models as Re-Ranking Agents
22 Pith papers cite this work, alongside 180 external citations. Polarity classification is still indexing.
22
Pith papers citing it
180
external citations · Crossref
hub tools
citation-role summary
background 3
dataset 1
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
F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.
TESSERA combines LLMs as local policy and evaluator with MCTS on knowledge graphs to compose mechanistic drug-disease explanations.
AgentSearchBench shows a consistent gap between semantic similarity and real agent performance on tasks, with execution-aware probing substantially improving retrieval and reranking quality.
HeadRank lifts preference optimization into attention space via entropy-regularized head selection and distribution regularizers to sharpen discriminability for efficient listwise reranking.
RSRank learns calibrated relevance scores from alignment between representational shifts induced by candidate documents and those from oracle document sets, enabling zero-threshold filtering.
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.
Rabtriever distills a generative reranker into an efficient bi-encoder using on-policy JEPA to achieve near-reranker accuracy with linear complexity on rationale-based retrieval.
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.
A two-phase data construction framework generates explanatory rationales from user feedback and applies uncertainty-based distillation to fine-tune lightweight LLMs as preference-aligned user simulators for recommender systems.
PETRA is a curated 1.36M-chunk petroleum-engineering retrieval dataset and pipeline that raises in-domain nDCG from 0.703 to 0.763 via score fusion and delivers 44% relative gain on an Earth Science benchmark through reranker adaptation on synthetic supervision.
SegTreeMem organizes agent conversation history as a temporally ordered segment tree and shows improved answer quality on long-horizon benchmarks when chronological order is preserved during insertion and retrieval.
Active learning applied to noisy LLM pairwise judgments improves NDCG@10 per call in budget-constrained reranking and enables unbiased aggregation via a randomized-direction single-call oracle.
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.
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 tuning-free LLM pipeline that annotates user histories with inferred motives and uses a reflection loop to correct search queries beats ID-based recommenders on a sparse industrial risk dataset.
Mira-Embeddings-V1 adapts embeddings for recruitment reranking by synthesizing positive and hard-negative samples with LLMs, then applies JD-JD contrastive and JD-CV triplet training plus a BoundaryHead MLP, lifting Recall@50 from 68.89% to 77.55% and Recall@200 from 0.5969 to 0.7047.
An adaptive thresholding mechanism combined with sliding-window reranking retrieves a query-dependent number of tables from large corpora, improving retrieval and downstream text-to-SQL performance on Spider, BIRD, and Spider 2.0.
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.
citing papers explorer
-
Quotient DAGs for Off-Policy Evaluation:Forward-Flow Importance Sampling and Exact Slate Propensities
Quotient DAGs enable forward-flow importance sampling and exact unordered slate propensities via Forward-DP for autoregressive slate loggers under set-sufficient interfaces.
-
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
-
F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking
F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.
-
LLM-Guided Monte Carlo Tree Search over Knowledge Graphs: Composing Mechanistic Explanations for Drug-Disease Pairs
TESSERA combines LLMs as local policy and evaluator with MCTS on knowledge graphs to compose mechanistic drug-disease explanations.
-
AgentSearchBench: A Benchmark for AI Agent Search in the Wild
AgentSearchBench shows a consistent gap between semantic similarity and real agent performance on tasks, with execution-aware probing substantially improving retrieval and reranking quality.
-
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.
-
RSRank: Learning Relevance from Representational Shifts
RSRank learns calibrated relevance scores from alignment between representational shifts induced by candidate documents and those from oracle document sets, enabling zero-threshold filtering.
-
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.
-
Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA
Rabtriever distills a generative reranker into an efficient bi-encoder using on-policy JEPA to achieve near-reranker accuracy with linear complexity on rationale-based retrieval.
-
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.
-
Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation
A two-phase data construction framework generates explanatory rationales from user feedback and applies uncertainty-based distillation to fine-tune lightweight LLMs as preference-aligned user simulators for recommender systems.
-
PETRA: Transforming Web Text for Petroleum-Engineering Domain Adaptation
PETRA is a curated 1.36M-chunk petroleum-engineering retrieval dataset and pipeline that raises in-domain nDCG from 0.703 to 0.763 via score fusion and delivers 44% relative gain on an Earth Science benchmark through reranker adaptation on synthetic supervision.
-
Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents
SegTreeMem organizes agent conversation history as a temporally ordered segment tree and shows improved answer quality on long-horizon benchmarks when chronological order is preserved during insertion and retrieval.
-
Active Learners as Efficient PRP Rerankers
Active learning applied to noisy LLM pairwise judgments improves NDCG@10 per call in budget-constrained reranking and enables unbiased aggregation via a randomized-direction single-call oracle.
-
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.
-
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%.
-
LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains
A tuning-free LLM pipeline that annotates user histories with inferred motives and uses a reflection loop to correct search queries beats ID-based recommenders on a sparse industrial risk dataset.
-
Mira-Embeddings-V1: Domain-Adapted Semantic Reranking for Recruitment via LLM-Synthesized Data
Mira-Embeddings-V1 adapts embeddings for recruitment reranking by synthesizing positive and hard-negative samples with LLMs, then applies JD-JD contrastive and JD-CV triplet training plus a BoundaryHead MLP, lifting Recall@50 from 68.89% to 77.55% and Recall@200 from 0.5969 to 0.7047.
-
Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method
An adaptive thresholding mechanism combined with sliding-window reranking retrieves a query-dependent number of tables from large corpora, improving retrieval and downstream text-to-SQL performance on Spider, BIRD, and Spider 2.0.
-
Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval
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.
- CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation