Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Massimo MelucciSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works154 from public data
- 526
- Humans or LLMs as the Judge? A Study on Judgement Bias436
A novel framework that is free from referencing groundtruth annotations for investigating bias and vulnerability of human- and LLM-as-a-judge, as well as the urgency of developing robust evaluation systems is proposed.
- Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models263
A comprehensive and challenging benchmark specifically designed to assess LLMs' mathematical reasoning at the Olympiad level, which shows that even the most advanced models, OpenAI o1-mini and OpenAI o1-preview, struggle with highly challenging Olympiad-level problems, highlighting significant challenges in Olympiad-level mathematical reasoning.
- Pre-trained Language Models in Biomedical Domain: A Systematic Survey256
The motivations of PLMs in the biomedical domain are discussed and the key concepts of pre-trained language models are introduced and a taxonomy of existing biomedical PLMs is proposed that categorizes them from various perspectives systematically.
- FinBen: A Holistic Financial Benchmark for Large Language Models220
FinBen is introduced, the first extensive open-source evaluation benchmark, including 36 datasets spanning 24 financial tasks, covering seven critical aspects: information extraction (IE), textual analysis, question answering (QA), text generation, risk management, forecasting, and decision-making.
- 206
- ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling196
The research team proposed OR-Instruct, a semiautomated data synthesis framework that generates high-quality training data tailored to specific optimization modeling requirements, and introduced IndustryOR, the first benchmark for evaluating LLMs’ performance on real-world OR problems.
- Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale150
This work refined medical image-text pairs from PubMed and employed MLLMs (GPT-4V) in an ‘unblinded’ capacity to denoise and reformat the data, resulting in the creation of the **PubMedVision** dataset with 1.3 million medical VQA samples.
- HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs142
The developed model, HuatuoGPT-II, has shown state-of-the-art performance in Chinese medicine domain on a number of benchmarks, and outperforms proprietary models like ChatGPT and GPT-4 in some aspects, especially in Traditional Chinese Medicine.
- A Multi-task Learning Framework for Opinion Triplet Extraction141
A novel view of ABSA as an opinion triplet extraction task is presented, and a multi-task learning framework to jointly extract aspect terms and opinion terms is proposed, and simultaneously parses sentiment dependencies between them with a biaffine scorer.
- Natural Language Reasoning, A Survey133
A clearer view of Natural Language Reasoning (NLR) in the field of Natural Language Processing (NLP) is proposed, both conceptually and practically, and defeasible reasoning is introduced as one of the most important future directions in NLR research.
- Detection of subtype blood cells using deep learning130
A CNN-based framework is built to automatically classify the blood cell images into subtypes of the cells, and the results show that the proposed model provide better results in terms of evaluation parameters.
- Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models123
This work introduces Generalized Instruction Tuning (called GLAN), a general and scalable method for instruction tuning of Large Language Models (LLMs) that exclusively utilizes a pre-curated taxonomy of human knowledge and capabilities as input and generates large-scale synthetic instruction data across all disciplines.
- A quantum-inspired multimodal sentiment analysis framework116
A Quantum-inspired Multimodal Sentiment Analysis (QMSA) framework that aims to fill the “semantic gap” and model the correlations between different modalities via density matrix and significantly outperforms a wide range of baselines and state-of-the-art methods.
- Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias114
This paper presents a novel framework named Unifying Cross-Lingual Medical Vision-Language Pre-Training (Med-UniC), designed to integrate multimodal medical data from the two most prevalent languages, English and Spanish, and proposes Cross-lingual Text Alignment Regularization (CTR) to explicitly unify cross-lingUAL semantic representations of medical reports originating from diverse language communities.
- End-to-End Quantum-like Language Models with Application to Question Answering103
A Neural Network based Quantum-like Language Model (NNQLM) is developed and applied to Question Answering, which represents a sentence and encodes a mixture of semantic subspaces and can be integrated into neural network architectures.
- 97
- CFN: A Complex-Valued Fuzzy Network for Sarcasm Detection in Conversations92
A complex-valued fuzzy network is proposed by leveraging the mathematical formalisms of quantum theory and fuzzy logic to address the intrinsic vagueness and uncertainty of human language in emotional expression and understanding in sarcasm detection.
- DialogueLLM: Context and emotion knowledge-tuned large language models for emotion recognition in conversations85
DialogueLLM, a context and emotion knowledge tuned LLM that is obtained by fine-tuning foundation large language models, is proposed, a context-aware model, which can accurately capture the dynamics of emotions throughout the dialogue.
- CNM: An Interpretable Complex-valued Network for Matching83
The proposed complex-valued network for matching (CNM) achieves comparable performances to strong CNN and RNN baselines on two benchmarking question answering (QA) datasets.
- 65
- What Does Your Smile Mean? Jointly Detecting Multi-Modal Sarcasm and Sentiment Using Quantum Probability60
The potential of QP as a mathematical framework is explored and a QP driven multi-task (QPM) learning framework is proposed, which involves a complex-valued multi-modal representation encoder, a quantum-like fusion network and a quantum measurement mechanism.
- 57
- Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts56
This work unify the input format by introducing visual and textual prompts, which serve as DETR-like queries that assist in extracting features when one of the modalities is missing, and proposes an effective yet straightforward scheme named PTUnifier to unify the two types.
- 53
- PLASTIC: Prioritize Long and Short-term Information in Top-n Recommendation using Adversarial Training53
This paper proposes a PLASTIC model, Prioritizing Long And Short-Term Information in top-n reCommendation using adversarial training and shows that this model exhibits significantly better performances on two widely used real-world datasets.
- 52
- Phoenix: Democratizing ChatGPT across Languages49
A large language model "Phoenix" is released, achieving competitive performance among open-source English and Chinese models while excelling in languages with limited resources (covering both Latin and non-Latin languages).
- Semantic Hilbert Space for Text Representation Learning49
A new framework that models different levels of semantic units on a single Semantic Hilbert Space, which naturally admits a non-linear semantic composition by means of a complex-valued vector word representation is proposed.
- 46
- A Multi-task Learning Approach for Image Captioning46
The experimental results demonstrate that the proposed Multi-task Learning Approach for Image Captioning achieves impressive results compared to other strong competitors.
- Spatio-temporal Contrastive Learning-enhanced GNNs for Session-based Recommendation44
A novel framework called Session-based Recommendation with Spatio-temporal Contrastive Learning-enhanced GNNs (RESTC), inspired by the uniformity and alignment properties of contrastive learning techniques, to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism.
- Quantum-Inspired Complex Word Embedding44
It is hypothesize that humans do not associate a single polarity or sentiment to each word, and makes use of the Hilbert Space representation of microscopic particles in Quantum Mechanics to subscribe a relative phase to eachword and investigates two quantum inspired models to derive the meaning of a combination of words.
- Exploration of Quantum Interference in Document Relevance Judgement Discrepancy43
This paper aims to explore and model the quantum interference in users’ relevance judgement about documents, caused by the presentation order of documents, and explains the judgement discrepancy in more depth in terms of four effects and the dynamics of document relevance judgement in Terms of the evolution of the information need subspace.
- 37
- A Survey of Quantum-cognitively Inspired Sentiment Analysis Models37
A background of quantum probability and quantum cognition at a theoretical level is provided, analyzing their advantages over classical theories in modeling the cognitive aspects of sentiment analysis and recent quantum-cognitively inspired models are introduced and discussed in detail.
- 35
- Document-level Relation Extraction with Relation Correlations35
It is argued that the correlations can not only transfer knowledge between data-rich relations and data-scarce ones to assist in the training of long-tailed relations, but also reflect semantic distance guiding the classifier to identify semantically close relations for multi-label entity pairs.
- A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers31
A comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate, and outlines a paradigm shift toward closed-loop systems where autonomous agents based on Sci-LLMs actively experiment, validate, and contribute to a living, evolving knowledge base.
- 29
- Exploring Extreme Parameter Compression for Pre-trained Language Models26
This work aims to explore larger compression ratios for PLMs, among which tensor decomposition is a potential but under-investigated one, and shows that the proposed method is orthogonal to existing compression methods like knowledge distillation.
- 25
- Complex-valued Neural Network-based Quantum Language Models24
A complex-valued neural network-based QLM solution called C-NNQLM is proposed to employ an end-to-end approach to build and train density matrices in a light-weight and differentiable manner, and it can therefore make use of external well-trained word vectors and supervised labels.
- A Quantum Query Expansion Approach for Session Search22
Empirical evaluation on the large-scale Clueweb12 dataset has shown that the proposed model is effective in the session search tasks, demonstrating the potential of developing novel and effective IR models based on intuitions and formalisms of QT.
- 21
- DPTDR: Deep Prompt Tuning for Dense Passage Retrieval21
The experimental results show that the proposed method, called DPTDR, outperforms previous state-of-the-art models on both MS-MARCO and Natural Questions and facilitates the industry, as it saves enormous efforts and costs of deployment and increases the utility of computing resources.
- 17
- 14
- 14
- RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques13
A new benchmark designed to assess the critique capabilities of Large Language Models, which employs a closed-loop methodology that evaluates the quality of corrections generated from critiques.
- 13
- Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM12
This work systematically analyzes multimodal data contamination using an analytical framework, MM-Detect, which defines two contamination categories-unimodal and cross-modal-and effectively quantifies contamination severity across multiple-choice and caption-based Visual Question Answering tasks.
- 12
- A Chinese Question Answering Approach Integrating Count-Based and Embedding-Based Features12
This work explores a Question Answering system which is characterized in Chinese for the QA task of NLPCC, and the ensemble strategy has achieved a good performance which is much stronger than the provided baselines.
- CoRT: Code-integrated Reasoning within Thinking11
CoRT is introduced, a post-training framework for teaching LRMs to leverage CI effectively and efficiently, by synthesizing code-integrated reasoning data through Hint-Engineering, which strategically inserts different hints at appropriate positions to optimize LRM-CI interaction.
- 10
- A distant supervision method based on paradigmatic relations for learning word embeddings10
A distant supervision method based on paradigmatic relations is proposed for learning word embeddings and it outperformed when compared against other existing models.
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- Real-Time Verification of Embodied Reasoning for Generative Skill Acquisition6
This work proposes VERGSA (Verifying Embodied Reasoning in Generative Skill Acquisition), a framework that systematically integrates real-time verification principles into embodied skill learning and establishes a seamless extension from verification of mathematical reasoning into embodied learning.
- 6
- 6
- 6
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.