0

Le Sun

Papers
36

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
36papers

Authored papers

36

Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces

arXiv 2026

2026

Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models

arXiv 2026

2026

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards

arXiv 2026

2026

MetaphorVU: Towards Metaphorical Video Understanding

arXiv 2026

2026

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides

arXiv 2025

2025

ConsistentChat: Building Skeleton-Guided Consistent Dialogues for Large Language Models from Scratch

arXiv 2025

2025

SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency

arXiv 2025

2025

DeepRAG: Thinking to Retrieval Step by Step for Large Language Models

arXiv 2025

2025

The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models

arXiv 2025

2025

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers

ICCV 2025

2025

PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing

arXiv 2025

2025

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models

arXiv 2025

2025

LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

arXiv 2025

2025

DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking

arXiv 2025

2025

Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch

arXiv 2025

2025

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

arXiv 2024

2024

Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models

arXiv 2024

2024

Academically intelligent LLMs are not necessarily socially intelligent

arXiv 2024

2024

SoFA: Shielded On-the-fly Alignment via Priority Rule Following

arXiv 2024

2024

Transferable Post-training via Inverse Value Learning

arXiv 2024

2024

Self-Retrieval: End-to-End Information Retrieval with One Large Language Model

arXiv 2024

2024

StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation

arXiv 2024

2024

READoc: A Unified Benchmark for Realistic Document Structured Extraction

arXiv 2024

2024

Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation

arXiv 2024

2024

Aligning Large Language Models via Self-Steering Optimization

arXiv 2024

2024

Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching

arXiv 2024

2024

Benchmarking Large Language Models in Retrieval-Augmented Generation

arXiv 2023

2023

ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases

arXiv 2023

2023

DBCopilot: Natural Language Querying over Massive Databases via Schema Routing

arXiv 2023

2023

Toward Unified Controllable Text Generation via Regular Expression Instruction

arXiv 2023

2023

Offline Pseudo Relevance Feedback for Efficient and Effective Single-pass Dense Retrieval

arXiv 2023

2023

The Life Cycle of Knowledge in Big Language Models: A Survey

arXiv 2023

2023

Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View

ACL 2022 5

2022

Few-shot Named Entity Recognition with Self-describing Networks

ACL 2022 5

2022

Enhanced Aspect-Based Sentiment Analysis Models with Progressive Self-supervised Attention Learning

arXiv 2021

2021

BERT-QE: Contextualized Query Expansion for Document Re-ranking

Findings of the Association for Computational Linguistics 2020

2020

Affiliations

No known affiliations.

Frequent co-authors

10

from 36 papers