A Hybrid LSTM-XGBoost Framework for Multi-Horizon Stock Return Prediction Across Diversified Equity Portfolios
为解决股票收益预测难题，提出结合LSTM与XGBoost的混合框架，通过处理市场特征和手工技术指标，实现多时间范围内的准确预测。
0 citationsRead paper
Selected work
Representative Papers
A Self Consistency Based Reranking for Narrative Question Answering
This work addresses the susceptibility of single-decoding approaches in narrative question answering to generation stochasticity, which often yields incomplete or inconsistent answers. To mitigate this issue, the authors propose a self-consistency reranking framework that requires no modification to the underlying model architecture. The method generates multiple candidate answers and reranks them based on semantic similarity, selecting the optimal response through consensus among the candidates. Evaluated on the NarrativeQA dataset, the approach demonstrates substantial performance gains when applied to both pretrained and fine-tuned language models: accuracy for Pegasus-Large improves from 72.50% to 87.07%, while FLAN-T5-Base achieves 86.66%. These results highlight the framework’s effectiveness in enhancing both the robustness and accuracy of narrative QA systems.
0 citationsRead paper
BLM-SGAN: Bidirectional Language Modeling for Semantic-Spatial Text-to-Image Generation
Existing text-to-image generation models are constrained by unidirectional language modeling, which struggles to capture long-range semantic dependencies and is susceptible to vanishing gradients. This work proposes BLM-SGAN, the first approach to integrate bidirectional language modeling into a GAN framework by incorporating BERT’s bidirectional attention mechanism. This enables joint modeling of semantic and spatial features, significantly enhancing text-image alignment and generation quality. By supporting long-sequence contextual modeling, BLM-SGAN overcomes the limitations of conventional unidirectional architectures. Evaluated on the CUB birds dataset, the method achieves an Inception Score of 5.45 ± 0.08, substantially outperforming state-of-the-art models such as SSA-GAN, DF-GAN, SD-GAN, and AttnGAN.
0 citationsRead paper
Improving Answer Extraction in Context-based Question Answering Systems Using LLMs
This study addresses the limitations of existing question-answering systems in handling complex or ambiguous queries, which often stem from insufficient contextual understanding, inconsistent responses, and poor cross-domain generalization. Building upon pre-trained large language models such as RoBERTa-base, the authors perform supervised fine-tuning on the SQuAD1.1 dataset to significantly enhance the model’s ability to accurately comprehend context and extract precise answers. Experimental results demonstrate that the fine-tuned model achieves strong performance across multiple evaluation metrics, including ROUGE-L (86.84%), BLEU (28.24%), and BERTScore (95.38%). These improvements effectively mitigate issues related to irrelevant or vague responses, thereby validating the approach’s notable gains in answer accuracy, relevance, and cross-domain adaptability.
0 citationsRead paper
MASF: A Multi-Model Adaptive Selection Framework for Abstractive Text summarization
Existing single-model summarization approaches often exhibit insufficient robustness and inconsistent output quality when handling texts with diverse structures and topics. To address this limitation, this work proposes a multi-model adaptive selection framework that integrates multiple fine-tuned Transformer-based summarization models to generate candidate summaries. The framework employs automatic evaluation metrics such as BERTScore to comprehensively assess candidates at both semantic and lexical levels, enabling adaptive selection of the highest-quality summary. Evaluated on the CNN/DailyMail dataset, the proposed method achieves a BERTScore of 88.63%, significantly outperforming prominent large language models including GPT-3-D2, Falcon-7B, and MPT-7B. This approach effectively enhances both the robustness and generation quality of abstractive summarization systems.
0 citationsRead paper
Recent publications
Latest Papers
A Hybrid LSTM-XGBoost Framework for Multi-Horizon Stock Return Prediction Across Diversified Equity Portfolios
为解决股票收益预测难题，提出结合LSTM与XGBoost的混合框架，通过处理市场特征和手工技术指标，实现多时间范围内的准确预测。
0 citationsRead paper
A Self Consistency Based Reranking for Narrative Question Answering
This work addresses the susceptibility of single-decoding approaches in narrative question answering to generation stochasticity, which often yields incomplete or inconsistent answers. To mitigate this issue, the authors propose a self-consistency reranking framework that requires no modification to the underlying model architecture. The method generates multiple candidate answers and reranks them based on semantic similarity, selecting the optimal response through consensus among the candidates. Evaluated on the NarrativeQA dataset, the approach demonstrates substantial performance gains when applied to both pretrained and fine-tuned language models: accuracy for Pegasus-Large improves from 72.50% to 87.07%, while FLAN-T5-Base achieves 86.66%. These results highlight the framework’s effectiveness in enhancing both the robustness and accuracy of narrative QA systems.
0 citationsRead paper
BLM-SGAN: Bidirectional Language Modeling for Semantic-Spatial Text-to-Image Generation
Existing text-to-image generation models are constrained by unidirectional language modeling, which struggles to capture long-range semantic dependencies and is susceptible to vanishing gradients. This work proposes BLM-SGAN, the first approach to integrate bidirectional language modeling into a GAN framework by incorporating BERT’s bidirectional attention mechanism. This enables joint modeling of semantic and spatial features, significantly enhancing text-image alignment and generation quality. By supporting long-sequence contextual modeling, BLM-SGAN overcomes the limitations of conventional unidirectional architectures. Evaluated on the CUB birds dataset, the method achieves an Inception Score of 5.45 ± 0.08, substantially outperforming state-of-the-art models such as SSA-GAN, DF-GAN, SD-GAN, and AttnGAN.
0 citationsRead paper
Improving Answer Extraction in Context-based Question Answering Systems Using LLMs
This study addresses the limitations of existing question-answering systems in handling complex or ambiguous queries, which often stem from insufficient contextual understanding, inconsistent responses, and poor cross-domain generalization. Building upon pre-trained large language models such as RoBERTa-base, the authors perform supervised fine-tuning on the SQuAD1.1 dataset to significantly enhance the model’s ability to accurately comprehend context and extract precise answers. Experimental results demonstrate that the fine-tuned model achieves strong performance across multiple evaluation metrics, including ROUGE-L (86.84%), BLEU (28.24%), and BERTScore (95.38%). These improvements effectively mitigate issues related to irrelevant or vague responses, thereby validating the approach’s notable gains in answer accuracy, relevance, and cross-domain adaptability.
0 citationsRead paper
MASF: A Multi-Model Adaptive Selection Framework for Abstractive Text summarization
Existing single-model summarization approaches often exhibit insufficient robustness and inconsistent output quality when handling texts with diverse structures and topics. To address this limitation, this work proposes a multi-model adaptive selection framework that integrates multiple fine-tuned Transformer-based summarization models to generate candidate summaries. The framework employs automatic evaluation metrics such as BERTScore to comprehensively assess candidates at both semantic and lexical levels, enabling adaptive selection of the highest-quality summary. Evaluated on the CNN/DailyMail dataset, the proposed method achieves a BERTScore of 88.63%, significantly outperforming prominent large language models including GPT-3-D2, Falcon-7B, and MPT-7B. This approach effectively enhances both the robustness and generation quality of abstractive summarization systems.
0 citationsRead paper