Dual-view training via polarity reversal improves instruction-following retrieval performance by 45% on the FollowIR benchmark using a 305M-parameter encoder.
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
years
2026 10representative citing papers
Multilingual pretraining develops translation in two phases: early copying driven by surface similarities, followed by generalizing mechanisms while copying is refined.
Code-switching creates a fundamental performance bottleneck for multilingual retrievers, causing drops of up to 27% on new benchmarks CSR-L and CS-MTEB, with embedding divergence as the key cause and vocabulary expansion insufficient to fix it.
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
MiMIC mitigates visual modality collapse and semantic misalignment in universal multimodal retrieval via fusion-in-decoder architecture and robust single-modality training.
MINTEval benchmark shows current memory-augmented systems average 27.9% accuracy on long-horizon interference tasks, limited by retrieval and memory construction with degradation from intervening updates.
Multilingual RAG rerankers exhibit language bias that limits cross-lingual evidence use, and the proposed LAURA method aligns ranking with downstream generation utility to reduce the bias and improve performance.
TGS-RAG adds graph-to-text re-ranking with global voting and text-to-graph orphan path bridging to improve precision and efficiency in multi-hop RAG over prior baselines.
A RAG pipeline with contextual PDF chunking, question-and-answer-aware retrieval and reranking using Qwen3 models reaches 0.96 accuracy on a Ukrainian multi-domain document QA shared task.
citing papers explorer
-
Dual-View Training for Instruction-Following Information Retrieval
Dual-view training via polarity reversal improves instruction-following retrieval performance by 45% on the FollowIR benchmark using a 305M-parameter encoder.
-
Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining
Multilingual pretraining develops translation in two phases: early copying driven by surface similarities, followed by generalizing mechanisms while copying is refined.
-
Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers
Code-switching creates a fundamental performance bottleneck for multilingual retrievers, causing drops of up to 27% on new benchmarks CSR-L and CS-MTEB, with embedding divergence as the key cause and vocabulary expansion insufficient to fix it.
-
Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
-
MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment
MiMIC mitigates visual modality collapse and semantic misalignment in universal multimodal retrieval via fusion-in-decoder architecture and robust single-modality training.
-
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
MINTEval benchmark shows current memory-augmented systems average 27.9% accuracy on long-horizon interference tasks, limited by retrieval and memory construction with degradation from intervening updates.
-
All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
Multilingual RAG rerankers exhibit language bias that limits cross-lingual evidence use, and the proposed LAURA method aligns ranking with downstream generation utility to reduce the bias and improve performance.
-
Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG
TGS-RAG adds graph-to-text re-ranking with global voting and text-to-graph orphan path bridging to improve precision and efficiency in multi-hop RAG over prior baselines.
-
Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding
A RAG pipeline with contextual PDF chunking, question-and-answer-aware retrieval and reranking using Qwen3 models reaches 0.96 accuracy on a Ukrainian multi-domain document QA shared task.
- To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios