paper-with-me

홈 › Papers

Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution

2025-01-31 · Tatiana Anikina, Arne Binder, David Harbecke, Stalin Varanasi, Leonhard Hennig, Simon Ostermann, Sebastian Möller, Josef van Genabith

In this work, we reimagine classical probing to evaluate knowledge transfer from simple source to more complex target tasks. Instead of probing frozen representations from a complex source task on diverse simple target probing tasks (as usually done in probing), we explore the effectiveness of embeddings from multiple simple source tasks on a single target task. We select coreference resolution, a linguistically complex problem requiring contextual understanding, as focus target task, and test the usefulness of embeddings from comparably simpler tasks tasks such as paraphrase detection, named entity recognition, and relation extraction. Through systematic experiments, we evaluate the impact of individual and combined task embeddings. Our findings reveal that task embeddings vary significantly in utility for coreference resolution, with semantic similarity tasks (e.g., paraphrase detection) proving most beneficial. Additionally, representations from intermediate layers of fine-tuned models often outperform those from final layers. Combining embeddings from multiple tasks consistently improves performance, with attention-based aggregation yielding substantial gains. These insights shed light on relationships between task-specific representations and their adaptability to complex downstream tasks, encouraging further exploration of embedding-level task transfer.

📄 PDF Abstract BibTeX arXiv:2501.19316

Code (0)

등록된 구현이 없습니다.

Tasks

coreference-resolutionCoreference Resolutionnamed-entity-recognitionNamed Entity RecognitionRelation ExtractionSemantic SimilaritySemantic Textual SimilarityTransfer Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

2025-12-14 · Yixin Tan, Zhe Yu, Jun Sakuma arxiv

Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs…

Improved transferability of self-supervised learning models through batch normalization finetuning

2024-08-15 · Applied Intelligence 2024 8 · Kirill Sirotkin, Marcos Escudero-Viñolo, Pablo Carballeira, Álvaro García-Martín

Abundance of unlabelled data and advances in Self-Supervised Learning (SSL) have made it the preferred choice in many transfer learning scenarios. Due to the rapid and ongoing development of SSL approaches, practitioners…

ClassificationFew-Shot LearningSelf-Supervised LearningTransfer Learning

Cross-Lingual Transfer of Cultural Knowledge: An Asymmetric Phenomenon

2025-06-02 · Chen Zhang, Zhiyuan Liao, Yansong Feng

Despite substantial research efforts evaluating how well large language models~(LLMs) handle global cultural diversity, the mechanisms behind their cultural knowledge acquisition, particularly in multilingual settings, r…

Cross-Lingual TransferDiversity

Cross-lingual Transfer of Monolingual Models

2021-09-15 · LREC 2022 6 · Evangelia Gogoulou, Ariel Ekgren, Tim Isbister, Magnus Sahlgren

Recent studies in zero-shot cross-lingual learning using multilingual models have falsified the previous hypothesis that shared vocabulary and joint pre-training are the keys to cross-lingual generalization. Inspired by …

Cross-Lingual TransferDomain Adaptation

Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing

2022-09-07 · Iro Laina, Yuki M. Asano, Andrea Vedaldi

Self-supervised visual representation learning has recently attracted significant research interest. While a common way to evaluate self-supervised representations is through transfer to various downstream tasks, we inst…

Representation Learning