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
- Jingren ZhouSuggested from co-authorship
- Weiran XuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works85 from public data
- FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research250
FlashRAG is an efficient and modular open-source toolkit designed to assist researchers in reproducing and comparing existing RAG methods and developing their own algorithms within a unified framework.
- InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Models120
This study pro-poses a novel approach, namely InstructERC, to reformulates the ERC task from a discriminative framework to a generative framework based on Large Language Models (LLMs) .
- ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models113
ChatKBQA is introduced, a novel and simple generate-then-retrieve KBQA framework, which proposes first generating the logical form with fine-tuned LLMs, then retrieving and replacing entities and relations with an unsupervised retrieval method, to improve both generation and retrieval more directly.
- Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation57
DPA-RAG is proposed, a universal framework designed to align diverse knowledge preferences within RAG systems and introduces a pre-aligned stage before vanilla Supervised Fine-tuning (SFT), enabling LLMs to implicitly capture knowledge aligned with their reasoning preferences, achieving LLMs' internal alignment.
- 54
- 49
- 41
- Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task38
A unified robustness evaluation framework based on the slot-filling task is proposed to systematically evaluate the dialogue understanding capability of LLMs in diverse input perturbation scenarios and some forward-looking suggestions are made to fuel the research in this direction.
- Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence37
Agent-World is presented, a self-evolving training arena for advancing general agent intelligence through scalable environments that consistently outperforms strong proprietary models and environment scaling baselines and reveals scaling trends in relation to environment diversity and self-evolution rounds, offering insights for building general agent intelligence.
- Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA36
This work introduces two novel structured knowledge-aware tasks, guiding the model to effectively learn the implicit relationship and better representations of complex subgraphs in Knowledge Base Question Answering.
- DotaMath: Decomposition of Thought with Code Assistance and Self-correction for Mathematical Reasoning31
This paper introduces a series of LLMs that employs the Decomposition of thought with code assistance and self-correction for mathematical reasoning, dubbed as DotaMath, which achieve remarkable performance compared to open-source LLMs across various in-domain and out-of-domain benchmarks.
- 28
- A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER24
A multi-task joint optimization framework with the semantic decomposing method is introduced, which facilitates the model to integrate two different semantic information for entity classification.
- Toward Generalist Autonomous Research via Hypothesis-Tree Refinement13
This work introduces Arbor, a general framework for autonomous research that combines a long-lived coordinator, short-lived executors, and Hypothesis Tree Refinement (HTR), a persistent tree that links hypotheses, artifacts, evidence, and distilled insights across time.
- We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?12
W E -M ATH is introduced, the first benchmark specifically designed to explore the problem-solving principles of LMMs’ reasoning process, and a novel four-dimensional metric is introduced to hierarchically assess inherent issues in LMMs’ reasoning process.
- A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Named Entity Recognition12
This paper proposed a Prototypical Semantic Decoupling method via joint Contrastive learning (PSDC) for few-shot NER that decouple class-specific prototypes and contextual semantic prototypes by two masking strategies to lead the model to focus on two different semantic information for inference.
- V-Oracle: Making Progressive Reasoning in Deciphering Oracle Bones for You and Me11
V-Oracle is proposed, an innovative framework that utilizes Large Multi-modal Models (LMMs) for interpreting OBS and applies principles of pictographic character formation and frames the task as a visual question-answering (VQA) problem, establishing a multi-step reasoning chain.
- 11
- 11
- 10
- 9
- 9
- 9
- 8
- 8
- 8
- 7
- 6
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Type-Aware Decoding Via Explicitly Aggregating Event Information for Document-Level Event Extraction–
- –
- –
- –
- –
- –
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.