paper-with-me

Papers

Leveraging Knowledge and Reinforcement Learning for Enhanced Reliability of Language Models

2023-08-25 · Nancy Tyagi, Surjodeep Sarkar, Manas Gaur

The Natural Language Processing(NLP) community has been using crowd sourcing techniques to create benchmark datasets such as General Language Understanding and Evaluation(GLUE) for training modern Language Models such as BERT. GLUE tasks measure the reliability scores using inter annotator metrics i.e. Cohens Kappa. However, the reliability aspect of LMs has often been overlooked. To counter this problem, we explore a knowledge-guided LM ensembling approach that leverages reinforcement learning to integrate knowledge from ConceptNet and Wikipedia as knowledge graph embeddings. This approach mimics human annotators resorting to external knowledge to compensate for information deficits in the datasets. Across nine GLUE datasets, our research shows that ensembling strengthens reliability and accuracy scores, outperforming state of the art.

📄 PDF Abstract BibTeX arXiv:2308.13467

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graph Embeddingsreinforcement-learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Residual Connection 설명 없음
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
WordPiece 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs

2025-07-03 · Yuzhang Xie, Hejie Cui, Ziyang Zhang, Jiaying Lu 외 arxiv

Medical diagnosis prediction plays a critical role in disease detection and personalized healthcare. While machine learning (ML) models have been widely adopted for this task, their reliance on supervised training limits…

Medical Diagnosis

Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning

2025-11-19 · Yudong Wang, Zhe Yang, Wenhan Ma, Zhifang Sui 외 arxiv

While reinforcement learning has unlocked unprecedented complex reasoning in large language models, it has also amplified their propensity for hallucination, creating a critical trade-off between capability and reliabili…

Reinforcement LearningQuestion Answering

CLST: Cold-Start Mitigation in Knowledge Tracing by Aligning a Generative Language Model as a Students' Knowledge Tracer

2024-06-13 · Heeseok Jung, Jaesang Yoo, Yohaan Yoon, Yeonju Jang

Knowledge tracing (KT), wherein students' problem-solving histories are used to estimate their current levels of knowledge, has attracted significant interest from researchers. However, most existing KT models were devel…

Domain GeneralizationKnowledge TracingLanguage ModelingLanguage Modelling+1

KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning

2024-06-24 · Dongyang Li, Taolin Zhang, Longtao Huang, Chengyu Wang 외

Knowledge-enhanced pre-trained language models (KEPLMs) leverage relation triples from knowledge graphs (KGs) and integrate these external data sources into language models via self-supervised learning. Previous works tr…

Hierarchical Reinforcement LearningKnowledge GraphsNatural Language Understandingreinforcement-learning+3

Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval

2025-09-08 · Hao Lin, Peitong Xie, Jingxue Chen, Jie Lin 외 arxiv

Retrieval-Augmented Generation (RAG) systems rely heavily on the retrieval stage, particularly the coarse-ranking process. Existing coarse-ranking optimization approaches often struggle to balance domain-specific knowled…

Reinforcement Learning