检索结果-内蒙古大学图书馆

A Survey of Recent Advances in Commonsense Knowledge Acquisition: Methods and Resources

Machine intelligence Research 2025年第2期22卷 201-218页

作者： Chenhao Wang Jiachun Li Yubo Chen Kang Liu Jun Zhao Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Beijing Academy of Artificial Intelligence Beijing 100049China

Imparting human-like commonsense to machines is a long-term goal in the artificial intelligence *** achieve this goal,constructing large-scale commonsense knowledge resources is an important *** recent years,due to increasing demand,commonsense knowledge has become a rapidly growing research field,resulting in a surge of new acquisition methods and corresponding *** advances have empowered a variety of downstream AI ***,constructing large-scale commonsense knowledge resources remains an ongoing and challenging *** is still difficult to efficiently collect large-scale,high-quality commonsense *** this paper,we systematically review recent advances in commonsense knowledge acquisition methods and resources,providing a comprehensive summary of recent research scope,the characteristics of different resources,and unsolved challenges.

关键词： Commonsense knowledge knowledge acquisition knowledge representation and processing knowledge resource knowledge engineering.

来源：评论

学校读者我要写书评

暂无评论

Towards Adaptive Mechanism Activation in Language Agent 31

Towards Adaptive Mechanism Activation in Language Agent

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Huang, Ziyang Zhao, Jun Liu, Kang The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences China

ISBN: (纸本)9798891761964

Language Agent could be endowed with different mechanisms for autonomous task accomplishment. Current agents typically rely on fixed mechanisms or a set of mechanisms activated in a predefined order, limiting their adaptation to varied potential task solution structures. To this end, this paper proposes Adaptive Language Agent Mechanism Activation Learning with Self-Exploration (ALAMA), which focuses on optimizing mechanism activation adaptability without reliance on expert models. Initially, it builds a harmonized agent framework (UniAct) to Unify different mechanisms via Actions. Then it leverages a training-efficient optimization method based on self-exploration to enable the UniAct to adaptively activate the appropriate mechanisms according to the potential characteristics of the task. Experimental results demonstrate significant improvements in downstream agent tasks, affirming the effectiveness of our approach in facilitating more dynamic and context-sensitive mechanism activation. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review of Bionic Robotic Flying Fish: Innovations in Cross-Medium Locomotion

A Review of Bionic Robotic Flying Fish: Innovations in Cross...

引用

2024 China Automation Congress, CAC 2024

作者： Meng, Lingchang Li, Haipeng Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9798350368604

The unique body structures of flying fish have endowed them with remarkable ability to swim underwater and glide through the air, which has attracted significant interests from researchers in the field of bionics. To help researchers understand the principles behind the motion of flying fish and provide a reference for developing bio-inspired robots capable of cross-medium locomotion, this paper introduces the morphological features and locomotion mechanisms of flying fish, and reviews relevant biomimetic research works. By comparing and analyzing the existing prototypes, this paper discusses the challenges in developing bionic robotic flying fish, which can replicate cross-medium locomotion of flying fish. Finally, the potential research directions are suggested. © 2024 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

KMatrix: A Flexible Heterogeneous Knowledge Enhancement Toolkit for Large Language Model

KMatrix: A Flexible Heterogeneous Knowledge Enhancement Tool...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Wu, Shun Wu, Di Luo, Kun Zhang, XueYou Zhao, Jun Liu, Kang The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China

ISBN: (纸本)9798891761674

Knowledge-Enhanced Large Language Models (K-LLMs) system enhances Large Language Models (LLMs) abilities using external knowledge. Existing K-LLMs toolkits mainly focus on free-textual knowledge, lacking support for heterogeneous knowledge like tables and knowledge graphs, and fall short in comprehensive datasets, models, and user-friendly experience. To address this gap, we introduce KMatrix: a flexible heterogeneous knowledge enhancement toolkit for LLMs including verbalizing-retrieval and parsing-query methods. Our modularity and control-logic flow diagram design flexibly supports the entire lifecycle of various complex K-LLMs systems, including training, evaluation, and deployment. To assist K-LLMs system research, a series of related knowledge, datasets, and models are integrated into our toolkit, along with performance analyses of K-LLMs systems enhanced by different types of knowledge. Using our toolkit, developers can rapidly build, evaluate, and deploy their own K-LLMs systems. Our toolkit and resources are available at here. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

ABSEval: An Agent-based Framework for Script Evaluation

ABSEval: An Agent-based Framework for Script Evaluation

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Liang, Sirui Zhang, Baoli Zhao, Jun Liu, Kang The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China

ISBN: (纸本)9798891761643

Recent research indicates that large language models (LLMs) possess a certain degree of script planning capability. However, there is still a lack of focused work on evaluating scripts generated by LLMs. The evaluation of scripts poses challenges due to their logical structure, sequential organization, adherence to commonsense constraints, and open-endedness. In this work, We introduced a novel script evaluation dataset, MCScript, consisting of more than 1,500 script evaluation tasks and steps, and developed an agent-based script evaluation framework, ABSEval, to collaboratively evaluate scripts generated by LLMs. Our experiments demonstrate that ABSEval provides superior accuracy and relevance, aligning closely with human evaluation. We evaluated the script planning capabilities of 15 mainstream LLMs and provided a detailed analysis. Furthermore, we observed phenomena like the key factor influencing the script planning ability of LLM is not parameter size and suggested improvements for evaluating open-ended questions. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Instance-Level Dynamic LoRAs Composition for Cross-Task Generalization

Instance-Level Dynamic LoRAs Composition for Cross-Task Gene...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Wang, Zhiqi He, Shizhu Liu, Kang Zhao, Jun The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761681

Large language models perform well on tasks that have undergone fine-tuning of instructions, but their performance on completely unseen tasks is often less than ideal. To overcome the challenge of cross-task generalization, task-level LoRAs combination is proposed, which does not require training a model for new tasks. Instead, it learns the LoRA modules combination weights based on a small number of samples to form the task model. However, task-level LoRAs combination only utilizes a few task modules due to its reliance on the weight enumeration method, and it also ignores the specificity between different instances. Therefore, we proposed an instance-level LoRAs composition for cross-task generalization, which selects appropriate multiple task LoRA modules for each input instance and dynamically determines the composition weights. Our experiments on publicly available datasets show that our method outperforms the typical method, LoraHub, in 16 out of 27 tasks. We release the source code at https://***/noname822/***. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models

Unlocking the Future: Exploring Look-Ahead Planning Mechanis...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Men, Tianyi Cao, Pengfei Jin, Zhuoran Chen, Yubo Liu, Kang Zhao, Jun The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Shanghai Artificial Intelligence Laboratory China

ISBN: (纸本)9798891761643

Planning, as the core module of agents, is crucial in various fields such as embodied agents, web navigation, and tool using. With the development of large language models (LLMs), some researchers treat large language models as intelligent agents to stimulate and evaluate their planning capabilities. However, the planning mechanism is still unclear. In this work, we focus on exploring the look-ahead planning mechanism in large language models from the perspectives of information flow and internal representations. First, we study how planning is done internally by analyzing the multi-layer perception (MLP) and multi-head self-attention (MHSA) components at the last token. We find that the output of MHSA in the middle layers at the last token can directly decode the decision to some extent. Based on this discovery, we further trace the source of MHSA by information flow, and we reveal that MHSA mainly extracts information from spans of the goal states and recent steps. According to information flow, we continue to study what information is encoded within it. Specifically, we explore whether future decisions have been encoded in advance in the representation of flow. We demonstrate that the middle and upper layers encode a few short-term future decisions to some extent when planning is successful. Overall, our research analyzes the look-ahead planning mechanisms of LLMs, facilitating future research on LLMs performing planning tasks. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering 31

Awakening Augmented Generation: Learning to Awaken Internal ...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Liao, Huanxuan He, Shizhu Xu, Yao Zhang, Yuanzhe Liu, Shengping Liu, Kang Zhao, Jun The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Unisound Beijing China

ISBN: (纸本)9798891761964

Retrieval-Augmented-Generation and Generation-Augmented-Generation have been proposed to enhance the knowledge required for question answering with Large Language Models (LLMs) by leveraging richer context. However, the former relies on external resources, and both require incorporating explicit documents into the context, which increases execution costs and susceptibility to noise data during inference. Recent works indicate that LLMs model rich knowledge, but it is often not effectively activated and awakened. Inspired by this, we propose a novel knowledge-augmented framework, Awakening-Augmented-Generation (AAG), which mimics the human ability to answer questions using only thinking and recalling to compensate for knowledge gaps, thereby awaking relevant knowledge in LLMs without relying on external resources. AAG consists of two key components for awakening richer context. Explicit awakening fine-tunes a context generator to create a synthetic, compressed document that functions as symbolic context. Implicit awakening utilizes a hypernetwork to generate adapters based on the question and synthetic document, which are inserted into LLMs to serve as parameter context. Experimental results on three datasets demonstrate that AAG exhibits significant advantages in both open-domain and closed-book settings, as well as in out-of-distribution generalization. Our code will be available at https://***/Xnhyacinth/IAG. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Reasons and Solutions for the Decline in Model Performance after Editing 38

Reasons and Solutions for the Decline in Model Performance a...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Huang, Xiusheng Liu, Jiaxiang Wang, Yequan Liu, Kang The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Beijing Academy of Artificial Intelligence Beijing China

Knowledge editing technology has received widespread attention for low-cost updates of incorrect or outdated knowledge in large-scale language models. However, recent research has found that edited models often exhibit varying degrees of performance degradation. The reasons behind this phenomenon and potential solutions have not yet been provided. In order to investigate the reasons for the performance decline of the edited model and optimize the editing method, this work explores the underlying reasons from both data and model perspectives. Specifically, 1) from a data perspective, to clarify the impact of data on the performance of editing models, this paper first constructs a Multi-Question Dataset (MQD) to evaluate the impact of different types of editing data on model performance. The performance of the editing model is mainly affected by the diversity of editing targets and sequence length, as determined through experiments. 2) From a model perspective, this article explores the factors that affect the performance of editing models. The results indicate a strong correlation between the L1-norm of the editing model layer and the editing accuracy, and clarify that this is an important factor leading to the bottleneck of editing performance. Finally, in order to improve the performance of the editing model, this paper further proposes a Dump for Sequence (D4S) method, which successfully overcomes the previous editing bottleneck by reducing the L1-norm of the editing layer, allowing users to perform multiple effective edits and minimizing model damage. Our code is available at https://***/nlpkeg/D4S. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning

LINKED: Eliciting, Filtering and Integrating Knowledge in La...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Li, Jiachun Cao, Pengfei Wang, Chenhao Jin, Zhuoran Chen, Yubo Liu, Kang Jiang, Xiaojian Xu, Jiexin Zhao, Jun School of Artificial Intelligence University of Chinese Academy of Sciences China The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences China China Merchants Bank China

ISBN: (纸本)9798891761681

Large language models (LLMs) sometimes demonstrate poor performance on knowledge-intensive tasks, commonsense reasoning is one of *** typically address these issues by retrieving related knowledge from knowledge graphs or employing self-enhancement methods to elicit knowledge in ***, noisy knowledge and invalid reasoning issues hamper their ability to answer questions *** this end, we propose a novel method named eLiciting, fIltering and iNtegrating Knowledge in large languagE moDel (LINKED).In it, we design a reward model to filter out the noisy knowledge and take the marginal consistent reasoning module to reduce invalid *** our comprehensive experiments on four complex commonsense reasoning benchmarks, our method outperforms SOTA baselines (up to 9.0% improvement of accuracy).Besides, to measure the positive and negative impact of the injected knowledge, we propose a new metric called effectiveness-preservation score for the knowledge enhancement ***, through extensive experiments, we conduct an in-depth analysis and find many meaningful conclusions about LLMs in commonsense reasoning tasks. © 2024 Association for Computational Linguistics.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：