Pith. sign in

REVIEW 4 cited by

From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.06595 v3 pith:DEB7ESKH submitted 2023-11-11 cs.CL

Xiaoqian Li , Ercong Nie , Sheng Liang This is my paper · ORCID
classification cs.CL
keywords classificationgenerationin-contextlearningperformancetasksacrossapproach
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The remarkable ability of Large Language Models (LLMs) to understand and follow instructions has sometimes been limited by their in-context learning (ICL) performance in low-resource languages. To address this, we introduce a novel approach that leverages cross-lingual retrieval-augmented in-context learning (CREA-ICL). By extracting semantically similar prompts from high-resource languages, we aim to improve the zero-shot performance of multilingual pre-trained language models (MPLMs) across diverse tasks. Though our approach yields steady improvements in classification tasks, it faces challenges in generation tasks. Our evaluation offers insights into the performance dynamics of retrieval-augmented in-context learning across both classification and generation domains.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MemCollab: Cross-Model Memory Collaboration via Contrastive Trajectory Distillation

    cs.AI 2026-03 conditional novelty 6.5 of 10

    Contrasting trajectories from heterogeneous LLM agents yields shared abstract reasoning constraints that transfer better than single-model or naively transferred memory.

  2. Enhancing Cross-task Transfer of Large Language Models via Activation Steering

    cs.CL 2025-07 conditional novelty 5.0 of 10

    CAST transfers knowledge across tasks by adding the average few-shot minus zero-shot activation difference from a high-resource task to a low-resource task's hidden state, improving accuracy without training or longer...

  3. HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers

    cs.IR 2025-09 conditional novelty 4.0 of 10

    By first fusing multiple retrievers within labeled and unlabeled sources with RRF, then merging z-score normalized lists, HF-RAG improves fact-verification F1 in-domain and out-of-domain.

  4. DoTA-RAG: Dynamic of Thought Aggregation RAG

    cs.CL 2025-06 conditional novelty 4.0 of 10

    DoTA-RAG combines query rewriting, namespace routing, dense retrieval, BM25 pruning, and reranking to answer questions over a 15M-document corpus, with reported correctness gains but fragile faithfulness under output caps.

Pith tools