目录 Content

• 目录 Content
• 会议论文 Conference Papers
• ⭐ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models
• ⭐PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents
• HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing
• ⭐ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
• [COLM 2024] StructLM: Towards Building Generalist Models for Structured Knowledge Grounding
• CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark
• ⭐[SIGIR-AP 2023] EALM: Introducing Multidimensional Ethical Alignment in Conversational Information Retrieval
• [ACL 2023] UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective
• ⭐[ACL 2023] Solving Math Word Problems via Cooperative Reasoning induced Language Models
• ⭐NER-to-MRC: Named-Entity Recognition Completely Solving as Machine Reading Comprehension
• ⭐[CVPR 2023] MAP: Modality-Agnostic Uncertainty-Aware Vision-Language Pre-training Model
• ⭐[EMNLP 2022] Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective
• [ACM MM 2022] Breaking Isolation: Multimodal Graph Fusion for Multimedia Recommendation by Edge-wise Modulation
• ⭐Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence
• ⭐Towards No.1 in CLUE Semantic Matching Challenge: Pre-trained Language Model Erlangshen with Propensity-Corrected Loss
• ⭐[EMNLP 2021] MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering
• ⭐[NTCIR 15] SKYMN at the NTCIR-15 DialEval-1 Task
• 期刊论文 Journal Papers
• ⭐[ACM TOIS 2024] SSR: Solving Named Entity Recognition Problems via a Single-stream Reasoner

会议论文 Conference Papers

⭐ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models

• Arxiv https://arxiv.org/abs/2406.20015
• Multi-level evaluation, Tool-augmented LLMs, Hallucination, Metrics, Benchmark
• Update @2024/06/28

⭐PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents

• Arxiv https://arxiv.org/abs/2406.13923
• Multimodal, Dataset, Data format, knowledge-intensive, MLLM, Training strategies
• Update @2024/06/20

HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing

• Arxiv https://arxiv.org/abs/2406.11683
• Role-playing mechanism, Screenwriting, Feedback
• Update @2024/06/17

⭐ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation

• Arxiv https://arxiv.org/abs/2406.09961
• Chart-to-Code, Evaluation, Metrics, MLLM, Multimodal, Benchmark
• Update @2024/06/14

[COLM 2024] StructLM: Towards Building Generalist Models for Structured Knowledge Grounding

• Arxiv https://arxiv.org/abs/2402.16671
• Structured knowlegde grounding, LLM, unified format, multiple sources
• Update @2024/02/27

CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark

• Arxiv https://arxiv.org/abs/2401.11944
• Multimodal understanding, chinese, evaluation
• Update @2024/01/22

⭐[SIGIR-AP 2023] EALM: Introducing Multidimensional Ethical Alignment in Conversational Information Retrieval

• ArXiv https://arxiv.org/abs/2310.00970
• Human ethics, multidimensional ethical alignment
• Update: @2023/09/10

[ACL 2023] UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective

• ACL 2023 https://aclanthology.org/2023.acl-long.907/
• ArXiv https://arxiv.org/abs/2210.16257
• Information extraction, unified framework, zero-shot, few-shot, finetuning, multitaak learning
• Update: @2023/06/18

⭐[ACL 2023] Solving Math Word Problems via Cooperative Reasoning induced Language Models

• ACL 2023 https://aclanthology.org/2023.acl-long.245/
• ArXiv https://arxiv.org/abs/2210.16257
• Reasoning, math problems, language models, improving LMs
• Update: @2023/05/04

⭐NER-to-MRC: Named-Entity Recognition Completely Solving as Machine Reading Comprehension

• ArXiv https://arxiv.org/abs/2305.03970
• Named-Entiry Recognition, Machine reading comprehension, Reasoning, Unified tasks
• Update: @2023/05/06

⭐[CVPR 2023] MAP: Modality-Agnostic Uncertainty-Aware Vision-Language Pre-training Model

• CVPR 2023 https://openaccess.thecvf.com/content/CVPR2023/html/Ji_MAP_Multimodal_Uncertainty-Aware_Vision-Language_Pre-Training_Model_CVPR_2023_paper.html
• ArXiv https://arxiv.org/abs/2210.05335
• Multimodal, Multimodal Pre-training, Distribution Representation, Vision-Language Downstream tasks
• Update: @2022/10/21

⭐[EMNLP 2022] Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective

• EMNLP 2022 https://aclanthology.org/2022.emnlp-main.474/
• ArXiv https://arxiv.org/abs/2210.08590
• NLP, Zero-shot, NLU, Unified Format
• Update: @2022/10/24

[ACM MM 2022] Breaking Isolation: Multimodal Graph Fusion for Multimedia Recommendation by Edge-wise Modulation

• ACM MM 2022 https://dl.acm.org/doi/abs/10.1145/3503161.3548399
• Multimedia, Multimodal Recommendation, Multimodal Graph. Fusion
• Update: @2022/10/10

⭐Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence

• ArXiv https://arxiv.org/abs/2209.02970
• NLP, Pre-trained Language Models, Deep Learning Framework, Benchmark, Chinese
• Update: @2022/09/07

⭐Towards No.1 in CLUE Semantic Matching Challenge: Pre-trained Language Model Erlangshen with Propensity-Corrected Loss

• ArXiv https://arxiv.org/abs/2208.02959
• NLP, Semantic Matching, Sentence Similarity, Propensity-Corrected Loss, CLUE

⭐[EMNLP 2021] MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering

• EMNLP 2021 https://aclanthology.org/2021.findings-emnlp.196/
• Multimodal interaction, VQA, trilinear transformers
• Update: @2021/10/07

⭐[NTCIR 15] SKYMN at the NTCIR-15 DialEval-1 Task

• NTCIR 15 http://research.nii.ac.jp/ntcir/workshop/OnlineProceedings15/pdf/ntcir/03-NTCIR15-DIALEVAL-WangJ.pdf
• NLP, Dialogue Evaluation, Multiple Models, Label-based Training
• Update: @2020/12/08

期刊论文 Journal Papers

⭐[ACM TOIS 2024] SSR: Solving Named Entity Recognition Problems via a Single-stream Reasoner

• ACM TOIS 2024 https://dl.acm.org/doi/10.1145/3655619
• Information Extraction, Named Entity Recognition, Human behaviors
• Update: @2024/04/15