Magnesium hydride(MgH_(2)),a promising high-capacity hydrogen storage material,is hindered by slow dehydrogenation kinetics.AIdriven catalyst discovery to address this is often hampered by the laborious extraction of ...Magnesium hydride(MgH_(2)),a promising high-capacity hydrogen storage material,is hindered by slow dehydrogenation kinetics.AIdriven catalyst discovery to address this is often hampered by the laborious extraction of data from unstructured literature.To overcome this,we introduce a transformative“LLM to Agent”framework that synergistically integrates Large Language Models(LLMs)for automated data curation with Machine Learning(ML)for predictive design.We automatically constructed a comprehensive database of 809 MgH_(2)catalysts(6555 data rows)with high fidelity and an~40-fold acceleration over manual methods.The resulting ML models achieved high accuracy(average R^(2)>0.91)in predicting dehydrogenation temperature and activation energy,subsequently guiding a Genetic Algorithm(GA)in an exploratory inverse design that autonomously uncovered key design principles for high-performance catalysts.Encouragingly,a strong alignment was found between these AI-discovered principles and the design strategies of recently reported,state-of-the-art experimental systems,providing substantial evidence for the validity of our approach.The framework culminates in Cat-Advisor,a novel,domain-adapted multi-agent system.Cat-Advisor translates ML predictions and retrieval-augmented knowledge into actionable design guidance,demonstrating capabilities that surpass those of general-purpose LLMs in this specialized domain.This work delivers a practical AI toolkit for accelerated materials discovery and advances the emerging Agent-based paradigm for designing next-generation energy technologies.展开更多
Objective To develop QingNangTCM,a specialized large language model(LLM)tailored for expert-level traditional Chinese medicine(TCM)question-answering and clinical reasoning,addressing the scarcity of domain-specific c...Objective To develop QingNangTCM,a specialized large language model(LLM)tailored for expert-level traditional Chinese medicine(TCM)question-answering and clinical reasoning,addressing the scarcity of domain-specific corpora and specialized alignment.Methods We constructed QnTCM_Dataset,a corpus of 100000 entries,by integrating data from ShenNong_TCM_Dataset and SymMap v2.0,and synthesizing additional samples via retrieval-augmented generation(RAG)and persona-driven generation.The dataset comprehensively covers diagnostic inquiries,prescriptions,and herbal knowledge.Utilizing P-Tuning v2,we fine-tuned the GLM-4-9B-Chat backbone to develop QingNangTCM.A multidimensional evaluation framework,assessing accuracy,coverage,consistency,safety,professionalism,and fluency,was established using metrics such as bilingual evaluation understudy(BLEU),recall-oriented understudy for gisting evaluation(ROUGE),metric for evaluation of translation with explicit ordering(METEOR),and LLM-as-a-Judge with expert review.Qualitative analysis was conducted across four simulated clinical scenarios:symptom analysis,disease treatment,herb inquiry,and failure cases.Baseline models included GLM-4-9BChat,DeepSeek-V2,HuatuoGPT-II(7B),and GLM-4-9B-Chat(freeze-tuning).Results QingNangTCM achieved the highest scores in BLEU-1/2/3/4(0.425/0.298/0.137/0.064),ROUGE-1/2(0.368/0.157),and METEOR(0.218),demonstrating a balanced and superior normalized performance profile of 0.900 across the dimensions of accuracy,coverage,and consistency.Although its ROUGE-L score(0.299)was lower than that of HuatuoGPT-II(7B)(0.351),it significantly outperformed domain-specific models in expert-validated win rates for professionalism(86%)and safety(73%).Qualitative analysis confirmed that the model strictly adheres to the“symptom-syndrome-pathogenesis-treatment”reasoning chain,though occasional misclassifications and hallucinations persisted when dealing with rare medicinal materials and uncommon syndromes.展开更多
This study compares the relative efficacy of the continuation task and the model-as-feedbackwriting (MAFW) task in EFL writing development. Ninety intermediate-level Chinese EFL learnerswere randomly assigned to a con...This study compares the relative efficacy of the continuation task and the model-as-feedbackwriting (MAFW) task in EFL writing development. Ninety intermediate-level Chinese EFL learnerswere randomly assigned to a continuation group, a MAFW group, and a control group, each with30 learners. A pretest and a posttest were used to gauge L2 writing development. Results showedthat the continuation task outperformed the MAFW task not only in enhancing the overall qualityof L2 writing, but also in promoting the quality of three components of L2 writing, namely, content,organization, and language. The finding has important implications for L2 writing teaching andlearning.展开更多
The target of much language teaching and learning is to make students approximate to native speakers.The only rightful speak ers of a language are its native speakers.Contrary to these contemporary views,however,this ...The target of much language teaching and learning is to make students approximate to native speakers.The only rightful speak ers of a language are its native speakers.Contrary to these contemporary views,however,this paper argues that the obligation of the lan guage teacher is to help students to use L2 effectively not to simply imitate native speaker.A successful L2 user who comes from the group of L2 learners can be a model for students.Therefore,non-native teachers with a high degree of language proficiency and good teaching skills can be ideal and qualified language teachers.展开更多
The author designed a questionnaire,emailed and interviewed thirty advanced L2 learners who work as L2 lecturers in a university to get a survey on the processing of fossilization in their foreign language learning an...The author designed a questionnaire,emailed and interviewed thirty advanced L2 learners who work as L2 lecturers in a university to get a survey on the processing of fossilization in their foreign language learning and teaching from the causes of purpose of learning,teaching tasks and other factors involved.All of the subjects thought that their command of the target language was not as good as a native speaker’s of target language in many aspects.That is,there existed fossilization among them.However,most of them agreed that their command of the target language was adequate for their professional and communication needs.Results also suggest that fossilization can be conscious to this group of L2 learners;it is deeply related with the L2 learners’ motivations;it can be affected by personal features such as ages,learning styles and teaching tasks;it is changeable and unpredictable; and it is difficult to eradicate.展开更多
This study aims at investigating the effect of using L 1 （Arabic Language） while teaching a target language （English Language） on the achievement in General English of foundation year students in King Abdulaziz Un...This study aims at investigating the effect of using L 1 （Arabic Language） while teaching a target language （English Language） on the achievement in General English of foundation year students in King Abdulaziz University. To achieve the purpose of the study, the researcher used an experimental design： an experimental group and a control group. The independent variable is using L1 while teaching English in very limited and specified areas. The dependent variable is students＇ achievement in general English. The statistics used is the t-test. The population of the study was all students enrolled in the foundation year 1431/1432 in the ELI （English Language Institute） at King Abdulaziz University. The sample of the study consisted of 50 students taking North Star in the sections A and B as a university requirement in the foundation year 1431/1432 in King Abdulaziz University. The results of the study were in favor of banning Arabic in the English language classroom as shown in the mean scores of the control and experimental groups in the tables. It is recommended that teachers and instructors should be trained to use teaching strategies that help them use English only in the English language classroom.展开更多
This paper investigates one aspect of the processing perspective in L2 （the second language） learning： the processing of new words. The article does not try to offer a comprehensive overview of language acquisition...This paper investigates one aspect of the processing perspective in L2 （the second language） learning： the processing of new words. The article does not try to offer a comprehensive overview of language acquisition mechanisms, but rather it intends to review more narrowly how our conceptual systems, governed by intricately linked networks of neural connections in the brain, make language development possible, at the same time creating some L2 processing problems. Vocabulary acquisition and application has been one of the main issues in English as a Second Language （ESL）/English as a Foreign Language （EFL） learning and teaching research. EFL instructors in Bosnia and Herzegovina, in particular, are coping with the effective vocabulary teaching approaches. The current paper will examine three principles based on cognitive linguistics （CL）, namely the study of categorization, prototype, and metaphor, and applications of these principles in formal vocabulary instruction in a Bosnian context of English learning in Bosnia and Herzegovina.展开更多
This study explored the distribution of three types of English formulaic language, which involves four categories in L1 Chinese L2 English learners’ speaking performance. In addition, it investigated the relationship...This study explored the distribution of three types of English formulaic language, which involves four categories in L1 Chinese L2 English learners’ speaking performance. In addition, it investigated the relationship between the English learners’ use of formulaic language and their spoken English fluency. A CCA(canonical correlation analysis) was conducted to examine the correlations between two sets of fluency variables(dependent variables) and linguistic variables of English formulaic language use(independent variables). The fluency variable set consists of:(1)temporal indices such as SR(speech rate), AR(articulation rate), MLR(mean length of run), and PTR(phonation time ratio);(2) linguistic variables of English formulaic language like F2 R(twoword formulaic sequences/run ratio, B3 R(three-word lexical bundles/run ratio), and B4 R(fourword lexical bundles/run ratio). These are calculated according to the frequency of the English formulaic language in the speech samples of the participants(n = 86) across three academic levels.The results indicate that the learners’ spoken English fluency is highly related to their use of English formulaic language. Its limitations and future research directions are also discussed.展开更多
基金supported by the Natural Science Foundation of Hebei Province(E2023502006)Fundamental Research Fund for the Central Universities(2025MS131).
文摘Magnesium hydride(MgH_(2)),a promising high-capacity hydrogen storage material,is hindered by slow dehydrogenation kinetics.AIdriven catalyst discovery to address this is often hampered by the laborious extraction of data from unstructured literature.To overcome this,we introduce a transformative“LLM to Agent”framework that synergistically integrates Large Language Models(LLMs)for automated data curation with Machine Learning(ML)for predictive design.We automatically constructed a comprehensive database of 809 MgH_(2)catalysts(6555 data rows)with high fidelity and an~40-fold acceleration over manual methods.The resulting ML models achieved high accuracy(average R^(2)>0.91)in predicting dehydrogenation temperature and activation energy,subsequently guiding a Genetic Algorithm(GA)in an exploratory inverse design that autonomously uncovered key design principles for high-performance catalysts.Encouragingly,a strong alignment was found between these AI-discovered principles and the design strategies of recently reported,state-of-the-art experimental systems,providing substantial evidence for the validity of our approach.The framework culminates in Cat-Advisor,a novel,domain-adapted multi-agent system.Cat-Advisor translates ML predictions and retrieval-augmented knowledge into actionable design guidance,demonstrating capabilities that surpass those of general-purpose LLMs in this specialized domain.This work delivers a practical AI toolkit for accelerated materials discovery and advances the emerging Agent-based paradigm for designing next-generation energy technologies.
基金Hebei Province Higher Education Scientific Research Project(QN2025367)Zhangjiakou City 2022 Municipal Science and Technology Plan Self-raised Fund Project(221105D)Hebei Province Education Science“14th Five-Year Plan”Project(2404224).
文摘Objective To develop QingNangTCM,a specialized large language model(LLM)tailored for expert-level traditional Chinese medicine(TCM)question-answering and clinical reasoning,addressing the scarcity of domain-specific corpora and specialized alignment.Methods We constructed QnTCM_Dataset,a corpus of 100000 entries,by integrating data from ShenNong_TCM_Dataset and SymMap v2.0,and synthesizing additional samples via retrieval-augmented generation(RAG)and persona-driven generation.The dataset comprehensively covers diagnostic inquiries,prescriptions,and herbal knowledge.Utilizing P-Tuning v2,we fine-tuned the GLM-4-9B-Chat backbone to develop QingNangTCM.A multidimensional evaluation framework,assessing accuracy,coverage,consistency,safety,professionalism,and fluency,was established using metrics such as bilingual evaluation understudy(BLEU),recall-oriented understudy for gisting evaluation(ROUGE),metric for evaluation of translation with explicit ordering(METEOR),and LLM-as-a-Judge with expert review.Qualitative analysis was conducted across four simulated clinical scenarios:symptom analysis,disease treatment,herb inquiry,and failure cases.Baseline models included GLM-4-9BChat,DeepSeek-V2,HuatuoGPT-II(7B),and GLM-4-9B-Chat(freeze-tuning).Results QingNangTCM achieved the highest scores in BLEU-1/2/3/4(0.425/0.298/0.137/0.064),ROUGE-1/2(0.368/0.157),and METEOR(0.218),demonstrating a balanced and superior normalized performance profile of 0.900 across the dimensions of accuracy,coverage,and consistency.Although its ROUGE-L score(0.299)was lower than that of HuatuoGPT-II(7B)(0.351),it significantly outperformed domain-specific models in expert-validated win rates for professionalism(86%)and safety(73%).Qualitative analysis confirmed that the model strictly adheres to the“symptom-syndrome-pathogenesis-treatment”reasoning chain,though occasional misclassifications and hallucinations persisted when dealing with rare medicinal materials and uncommon syndromes.
文摘This study compares the relative efficacy of the continuation task and the model-as-feedbackwriting (MAFW) task in EFL writing development. Ninety intermediate-level Chinese EFL learnerswere randomly assigned to a continuation group, a MAFW group, and a control group, each with30 learners. A pretest and a posttest were used to gauge L2 writing development. Results showedthat the continuation task outperformed the MAFW task not only in enhancing the overall qualityof L2 writing, but also in promoting the quality of three components of L2 writing, namely, content,organization, and language. The finding has important implications for L2 writing teaching andlearning.
文摘The target of much language teaching and learning is to make students approximate to native speakers.The only rightful speak ers of a language are its native speakers.Contrary to these contemporary views,however,this paper argues that the obligation of the lan guage teacher is to help students to use L2 effectively not to simply imitate native speaker.A successful L2 user who comes from the group of L2 learners can be a model for students.Therefore,non-native teachers with a high degree of language proficiency and good teaching skills can be ideal and qualified language teachers.
文摘The author designed a questionnaire,emailed and interviewed thirty advanced L2 learners who work as L2 lecturers in a university to get a survey on the processing of fossilization in their foreign language learning and teaching from the causes of purpose of learning,teaching tasks and other factors involved.All of the subjects thought that their command of the target language was not as good as a native speaker’s of target language in many aspects.That is,there existed fossilization among them.However,most of them agreed that their command of the target language was adequate for their professional and communication needs.Results also suggest that fossilization can be conscious to this group of L2 learners;it is deeply related with the L2 learners’ motivations;it can be affected by personal features such as ages,learning styles and teaching tasks;it is changeable and unpredictable; and it is difficult to eradicate.
文摘This study aims at investigating the effect of using L 1 （Arabic Language） while teaching a target language （English Language） on the achievement in General English of foundation year students in King Abdulaziz University. To achieve the purpose of the study, the researcher used an experimental design： an experimental group and a control group. The independent variable is using L1 while teaching English in very limited and specified areas. The dependent variable is students＇ achievement in general English. The statistics used is the t-test. The population of the study was all students enrolled in the foundation year 1431/1432 in the ELI （English Language Institute） at King Abdulaziz University. The sample of the study consisted of 50 students taking North Star in the sections A and B as a university requirement in the foundation year 1431/1432 in King Abdulaziz University. The results of the study were in favor of banning Arabic in the English language classroom as shown in the mean scores of the control and experimental groups in the tables. It is recommended that teachers and instructors should be trained to use teaching strategies that help them use English only in the English language classroom.
文摘This paper investigates one aspect of the processing perspective in L2 （the second language） learning： the processing of new words. The article does not try to offer a comprehensive overview of language acquisition mechanisms, but rather it intends to review more narrowly how our conceptual systems, governed by intricately linked networks of neural connections in the brain, make language development possible, at the same time creating some L2 processing problems. Vocabulary acquisition and application has been one of the main issues in English as a Second Language （ESL）/English as a Foreign Language （EFL） learning and teaching research. EFL instructors in Bosnia and Herzegovina, in particular, are coping with the effective vocabulary teaching approaches. The current paper will examine three principles based on cognitive linguistics （CL）, namely the study of categorization, prototype, and metaphor, and applications of these principles in formal vocabulary instruction in a Bosnian context of English learning in Bosnia and Herzegovina.
文摘This study explored the distribution of three types of English formulaic language, which involves four categories in L1 Chinese L2 English learners’ speaking performance. In addition, it investigated the relationship between the English learners’ use of formulaic language and their spoken English fluency. A CCA(canonical correlation analysis) was conducted to examine the correlations between two sets of fluency variables(dependent variables) and linguistic variables of English formulaic language use(independent variables). The fluency variable set consists of:(1)temporal indices such as SR(speech rate), AR(articulation rate), MLR(mean length of run), and PTR(phonation time ratio);(2) linguistic variables of English formulaic language like F2 R(twoword formulaic sequences/run ratio, B3 R(three-word lexical bundles/run ratio), and B4 R(fourword lexical bundles/run ratio). These are calculated according to the frequency of the English formulaic language in the speech samples of the participants(n = 86) across three academic levels.The results indicate that the learners’ spoken English fluency is highly related to their use of English formulaic language. Its limitations and future research directions are also discussed.
