{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:17:09Z","timestamp":1783153029793,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","funder":[{"name":"National Key R&D Program of China","award":["2024YFB4505904"],"award-info":[{"award-number":["2024YFB4505904"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792164","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:28:36Z","timestamp":1777296516000},"page":"5120-5131","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TraceLLM: Evaluating and Exploring Large Language Models on Trace Analysis in Microservice-based Web Applications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7431-9809","authenticated-orcid":false,"given":"Tong","family":"Zhou","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3376-2581","authenticated-orcid":false,"given":"Xin","family":"Peng","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5496-4336","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Samsung Electronics (China) R&D Centre, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4195-0122","authenticated-orcid":false,"given":"Chaofeng","family":"Sha","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1432-9957","authenticated-orcid":false,"given":"Chenxi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8036-7245","authenticated-orcid":false,"given":"Zicheng","family":"Yuan","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3331-7733","authenticated-orcid":false,"given":"Senyu","family":"Xie","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Ivan Beschastnikh, Tamara Munzner, and Jonathan Mace.","author":"Anand Vaastav","year":"2020","unstructured":"Vaastav Anand, Matheus Stolet, Thomas James Davidson, Ivan Beschastnikh, Tamara Munzner, and Jonathan Mace. 2020. Aggregate-driven trace visualizations for performance debugging. CoRR, abs\/2010.13681."},{"key":"e_1_3_2_1_2_1","first-page":"78142","article-title":"Benchmarking foundation models with language-model-as-an-examiner","volume":"36","author":"Yushi Bai","year":"2023","unstructured":"Yushi Bai et al. 2023. Benchmarking foundation models with language-model-as-an-examiner. Advances in Neural Information Processing Systems, 36, 78142--78167.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","unstructured":"Yejin Bang et al. 2023. A multitask multilingual multimodal evaluation of chat-gpt on reasoning hallucination and interactivity. arXiv preprint arXiv:2302.04023."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Andr\u00e9 Bento Jaime Correia Ricardo Filipe Filipe Ara\u00fajo and Jorge Cardoso. 2021. Automated analysis of distributed tracing: challenges and research directions. J. Grid Comput.","DOI":"10.1007\/s10723-021-09551-5"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Ning Bian Xianpei Han Le Sun Hongyu Lin Yaojie Lu Ben He Shanshan Jiang and Bin Dong. 2023. Chatgpt is a knowledgeable but inexperienced solver: an investigation of commonsense problem in large language models. arXiv preprint arXiv:2303.16421.","DOI":"10.63317\/32y85i5g9gso"},{"key":"e_1_3_2_1_6_1","unstructured":"Shaked Brody Uri Alon and Eran Yahav. 2021. How attentive are graph attention networks? arXiv preprint arXiv:2105.14491."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Rui Cao and Qiao Wang. 2024. An evaluation of standard statistical models and llms on time series forecasting. CoRR abs\/2408.04867.","DOI":"10.1109\/FMLDS63805.2024.00098"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Yupeng Chang et al. 2024. A survey on evaluation of large language models. ACM transactions on intelligent systems and technology 15 3 1--45.","DOI":"10.1145\/3641289"},{"key":"e_1_3_2_1_9_1","volume-title":"https:\/\/chaosblade.io\/","author":"Retrieved February","year":"2025","unstructured":"ChaosBlade. 2025. Retrieved February 8, 2025. (2025). https:\/\/chaosblade.io\/."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Joseph Chervenak Harry Lieman Miranda Blanco-Breindel and Sangita Jindal. 2023. The promise and peril of using a large language model to obtain clinical information: chatgpt performs strongly as a fertility counseling tool with limitations. Fertility and sterility 120 3 575--583.","DOI":"10.1016\/j.fertnstert.2023.05.151"},{"key":"e_1_3_2_1_11_1","volume-title":"https:\/\/medium.com\/jaegertracing\/trace-comparisons-arrive-in-jaeger-1--7-a97ad5e2d05d","author":"Compare Jaeger","year":"2018","unstructured":"Jaeger Compare. 2018. Retrieved February 8, 2025. (2018). https:\/\/medium.com\/jaegertracing\/trace-comparisons-arrive-in-jaeger-1--7-a97ad5e2d05d."},{"key":"e_1_3_2_1_12_1","volume-title":"Logeval: A comprehensive benchmark suite for large language models in log analysis. CoRR.","author":"Tianyu Cui","year":"2024","unstructured":"Tianyu Cui et al. 2024. Logeval: A comprehensive benchmark suite for large language models in log analysis. CoRR."},{"key":"e_1_3_2_1_13_1","volume-title":"https:\/\/huggingface.co\/deepseek-ai\/DeepSeek-R1-Distill-Llama-8B","author":"Retrieved B.","year":"2025","unstructured":"DeepSeek-R1-Distill-Llama-8B. 2025. Retrieved February 8, 2025. (2025). https:\/\/huggingface.co\/deepseek-ai\/DeepSeek-R1-Distill-Llama-8B."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3464298.3493396"},{"key":"e_1_3_2_1_15_1","volume-title":"https:\/\/llamafactory.readthedocs.io\/en\/latest\/","author":"Factory MA","year":"2025","unstructured":"LLaMA Factory. 2025. Retrieved February 8, 2025. (2025). https:\/\/llamafactory.readthedocs.io\/en\/latest\/."},{"key":"e_1_3_2_1_16_1","unstructured":"Bahare Fatemi Jonathan Halcrow and Bryan Perozzi. 2023. Talk like a graph: encoding graphs for large language models. arXiv preprint arXiv:2310.04560."},{"key":"e_1_3_2_1_17_1","volume-title":"https:\/\/x.com\/goodside\/status\/1830470374321963103","author":"Goodside Riley","year":"2024","unstructured":"Riley Goodside. 2024. Retrieved February 8, 2025. (2024). https:\/\/x.com\/goodside\/status\/1830470374321963103."},{"key":"e_1_3_2_1_18_1","unstructured":"Zhibin Gou Zhihong Shao Yeyun Gong Yelong Shen Yujiu Yang Minlie Huang Nan Duan and Weizhu Chen. 2023. Tora: a tool-integrated reasoning agent for mathematical problem solving. arXiv preprint arXiv:2309.17452."},{"key":"e_1_3_2_1_19_1","volume-title":"https:\/\/openai.com\/index\/hello-gpt-4o\/","author":"Retrieved February","year":"2024","unstructured":"GPT-4o. 2024. Retrieved February 8, 2025. (2024). https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"e_1_3_2_1_20_1","unstructured":"Jiayan Guo Lun Du Hengyu Liu Mengyu Zhou Xinyi He and Shi Han. 2023. Gpt4graph: can large language models understand graph structured data? an empirical evaluation and benchmarking. arXiv preprint arXiv:2305.15066."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417066"},{"key":"e_1_3_2_1_22_1","first-page":"2","article-title":"Lora: low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. Lora: low-rank adaptation of large language models. ICLR, 1, 2, 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486994"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","first-page":"72096","DOI":"10.52202\/075280-3155","article-title":"Language is not all you need: aligning perception with language models","volume":"36","author":"Shaohan Huang","year":"2023","unstructured":"Shaohan Huang et al. 2023. Language is not all you need: aligning perception with language models. Advances in Neural Information Processing Systems, 36, 72096--72109.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","volume-title":"https:\/\/www.jaegertracing.io\/","author":"Retrieved February","year":"2025","unstructured":"Jaeger. 2025. Retrieved February 8, 2025. (2025). https:\/\/www.jaegertracing.io\/."},{"key":"e_1_3_2_1_26_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Ming","year":"2024","unstructured":"Ming Jin et al. 2024. Time-llm: time series forecasting by reprogramming large language models. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7--11, 2024."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-021-10063-9"},{"key":"e_1_3_2_1_28_1","volume-title":"2021 IEEE\/ACM 29th International Symposium on Quality of Service (IWQOS). IEEE, 1--10","author":"Zeyan","unstructured":"Zeyan Li et al. 2021. Practical root cause localization for microservice systems via trace analysis. In 2021 IEEE\/ACM 29th International Symposium on Quality of Service (IWQOS). IEEE, 1--10."},{"key":"e_1_3_2_1_29_1","volume-title":"2020 IEEE 31st International Symposium on Software Reliability Engineering (ISSRE). IEEE, 48--58","author":"Ping","unstructured":"Ping Liu et al. 2020. Unsupervised detection of microservice trace anomalies through service-level deep bayesian networks. In 2020 IEEE 31st International Symposium on Software Reliability Engineering (ISSRE). IEEE, 48--58."},{"key":"e_1_3_2_1_30_1","unstructured":"Yilun Liu et al. 2024. Loglm: from task-based to instruction-based automated log analysis. arXiv preprint arXiv:2410.09352."},{"key":"e_1_3_2_1_31_1","volume-title":"https:\/\/grafana.com\/oss\/loki\/","author":"Loki Grafana","year":"2025","unstructured":"Grafana Loki. 2025. Retrieved February 8, 2025. (2025). https:\/\/grafana.com\/oss\/loki\/."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3174631"},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on Machine learning. PMLR, 23803--23828","author":"Mao Anqi","year":"2023","unstructured":"Anqi Mao, Mehryar Mohri, and Yutao Zhong. 2023. Cross-entropy loss functions: theoretical analysis and applications. In International conference on Machine learning. PMLR, 23803--23828."},{"key":"e_1_3_2_1_34_1","volume-title":"https:\/\/huggingface.co\/meta-llama\/Meta-Llama-3--8B","author":"Retrieved February","year":"2025","unstructured":"Meta-Llama-3--8B-Instruct. 2025. Retrieved February 8, 2025. (2025). https:\/\/huggingface.co\/meta-llama\/Meta-Llama-3--8B."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2019.00038"},{"key":"e_1_3_2_1_36_1","volume-title":"https:\/\/github.com\/GoogleCloudPlatform\/microservices-demo","author":"Retrieved February","year":"2025","unstructured":"OnlineBoutique. 2025. Retrieved February 8, 2025. (2025). https:\/\/github.com\/GoogleCloudPlatform\/microservices-demo."},{"key":"e_1_3_2_1_37_1","volume-title":"https:\/\/opentelemetry.io\/","author":"Retrieved February","year":"2025","unstructured":"OpenTelemetry. 2025. Retrieved February 8, 2025. (2025). https:\/\/opentelemetry.io\/."},{"key":"e_1_3_2_1_38_1","volume-title":"https:\/\/opentracing.io\/","author":"Retrieved February","year":"2025","unstructured":"OpenTracing. 2025. Retrieved February 8, 2025. (2025). https:\/\/opentracing.io\/."},{"key":"e_1_3_2_1_39_1","volume-title":"https:\/\/huggingface.co\/Qwen\/Qwen3--8B","author":"Retrieved B.","year":"2025","unstructured":"Qwen3--8B. 2025. Retrieved February 8, 2025. (2025). https:\/\/huggingface.co\/Qwen\/Qwen3--8B."},{"key":"e_1_3_2_1_40_1","volume-title":"https:\/\/github.com\/hiyouga\/LLaMA-Factory","author":"Factory Repo MA","year":"2025","unstructured":"LLaMA Factory Repo. 2025. Retrieved February 8, 2025. (2025). https:\/\/github.com\/hiyouga\/LLaMA-Factory."},{"key":"e_1_3_2_1_41_1","volume-title":"Mike Burrows, Pat Stephenson, Manoj Plakal, Donald Beaver, Saul Jaspan, and Chandan Shanbhag.","author":"Sigelman Benjamin H","year":"2010","unstructured":"Benjamin H Sigelman, Luiz Andr\u00e9 Barroso, Mike Burrows, Pat Stephenson, Manoj Plakal, Donald Beaver, Saul Jaspan, and Chandan Shanbhag. 2010. Dapper, a large-scale distributed systems tracing infrastructure."},{"key":"e_1_3_2_1_42_1","volume-title":"https:\/\/skywalking.apache.org\/","author":"SkyWalking Apache","year":"2025","unstructured":"Apache SkyWalking. 2025. Retrieved February 8, 2025. (2025). https:\/\/skywalking.apache.org\/."},{"key":"e_1_3_2_1_43_1","unstructured":"Jianheng Tang Qifan Zhang Yuhan Li Nuo Chen and Jia Li. 2024. Grapharena: evaluating and exploring large language models on graph computation. arXiv preprint arXiv:2407.00379."},{"key":"e_1_3_2_1_44_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Tang Jianheng","year":"2025","unstructured":"Jianheng Tang, Qifan Zhang, Yuhan Li, Nuo Chen, and Jia Li. 2025. Grapharena: evaluating and exploring large language models on graph computation. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.18326852"},{"key":"e_1_3_2_1_46_1","unstructured":"Petar Velickovic Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio Yoshua Bengio et al. 2017. Graph attention networks. stat 1050 20 10--48550."},{"key":"e_1_3_2_1_47_1","unstructured":"Xilong Wang Hao Fu Jindong Wang and Neil Zhenqiang Gong. 2024. Stringllm: understanding the string processing capability of large language models. arXiv preprint arXiv:2410.01208."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Zhe Xie Zeyan Li Xiao He Longlong Xu Xidao Wen Tieying Zhang Jianjun Chen Rui Shi and Dan Pei. 2024. Chatts: aligning time series with llms via synthetic data for enhanced understanding and reasoning. arXiv preprint arXiv:2412.03104.","DOI":"10.14778\/3742728.3742735"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449905"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639088"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510180"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549146"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE55969.2022.00032"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3392335"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00033"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2018.2887384"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2018.2887384"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338961"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183440.3194991"},{"key":"e_1_3_2_1_61_1","volume-title":"https:\/\/zipkin.io\/","author":"Retrieved February","year":"2025","unstructured":"Zipkin. 2025. Retrieved February 8, 2025. (2025). https:\/\/zipkin.io\/."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:33:50Z","timestamp":1783150430000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":61,"alternative-id":["10.1145\/3774904.3792164","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792164","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}