{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:23:39Z","timestamp":1764782619672,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,7]]},"DOI":"10.1145\/3767695.3769499","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:14:58Z","timestamp":1764782098000},"page":"343-352","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8670-1627","authenticated-orcid":false,"given":"Xuancheng","family":"Li","sequence":"first","affiliation":[{"name":"DCST, Tsinghua Univesity, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8766-8610","authenticated-orcid":false,"given":"Haitao","family":"Li","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3530-3787","authenticated-orcid":false,"given":"Yujia","family":"Zhou","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5030-709X","authenticated-orcid":false,"given":"Qingyao","family":"Ai","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0140-4512","authenticated-orcid":false,"given":"Yiqun","family":"Liu","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations. arXiv preprint arXiv:2410.10136","author":"Agrawal Garima","year":"2024","unstructured":"Garima Agrawal, Sashank Gummuluri, and Cosimo Spera. 2024. Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations. arXiv preprint arXiv:2410.10136 (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"Longbench: A bilingual, multitask benchmark for long context understanding. arXiv preprint arXiv:2308.14508","author":"Bai Yushi","year":"2023","unstructured":"Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, et al. 2023. Longbench: A bilingual, multitask benchmark for long context understanding. arXiv preprint arXiv:2308.14508 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs. arXiv preprint arXiv:2406.02376","author":"Cao Zhiwei","year":"2024","unstructured":"Zhiwei Cao, Qian Cao, Yu Lu, Ningxin Peng, Luyang Huang, Shanbo Cheng, and Jinsong Su. 2024. Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs. arXiv preprint arXiv:2406.02376 (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"e_1_3_2_1_5_1","volume-title":"Longlora: Efficient fine-tuning of long-context large language models. arXiv preprint arXiv:2309.12307","author":"Chen Yukang","year":"2023","unstructured":"Yukang Chen, Shengju Qian, Haotian Tang, Xin Lai, Zhijian Liu, Song Han, and Jiaya Jia. 2023. Longlora: Efficient fine-tuning of long-context large language models. arXiv preprint arXiv:2309.12307 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token. arXiv preprint arXiv:2405.13792","author":"Cheng Xin","year":"2024","unstructured":"Xin Cheng, Xun Wang, Xingxing Zhang, Tao Ge, Si-Qing Chen, Furu Wei, Huishuai Zhang, and Dongyan Zhao. 2024. xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token. arXiv preprint arXiv:2405.13792 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Adapting language models to compress contexts. arXiv preprint arXiv:2305.14788","author":"Chevalier Alexis","year":"2023","unstructured":"Alexis Chevalier, AlexanderWettig, Anirudh Ajith, and Danqi Chen. 2023. Adapting language models to compress contexts. arXiv preprint arXiv:2305.14788 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657834"},{"key":"e_1_3_2_1_9_1","volume-title":"Probing explicit and implicit gender bias through llm conditional text generation. arXiv preprint arXiv:2311.00306","author":"Dong Xiangjue","year":"2023","unstructured":"Xiangjue Dong, Yibo Wang, Philip S Yu, and James Caverlee. 2023. Probing explicit and implicit gender bias through llm conditional text generation. arXiv preprint arXiv:2311.00306 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671470"},{"key":"e_1_3_2_1_11_1","volume-title":"Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997 (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"Incontext autoencoder for context compression in a large language model. arXiv preprint arXiv:2307.06945","author":"Ge Tao","year":"2023","unstructured":"Tao Ge, Jing Hu, Lei Wang, Xun Wang, Si-Qing Chen, and Furu Wei. 2023. Incontext autoencoder for context compression in a large language model. arXiv preprint arXiv:2307.06945 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Generalized huber loss for robust learning and its efficient minimization for a robust statistics. arXiv preprint arXiv:2108.12627","author":"Gokcesu Kaan","year":"2021","unstructured":"Kaan Gokcesu and Hakan Gokcesu. 2021. Generalized huber loss for robust learning and its efficient minimization for a robust statistics. arXiv preprint arXiv:2108.12627 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Cheng-Yu Hsieh Yung-Sung Chuang Chun-Liang Li Zifeng Wang Long T Le Abhishek Kumar James Glass Alexander Ratner Chen-Yu Lee Ranjay Krishna et al. 2024. Found in the middle: Calibrating positional attention bias improves long context utilization. arXiv preprint arXiv:2406.16008 (2024).","DOI":"10.18653\/v1\/2024.findings-acl.890"},{"key":"e_1_3_2_1_15_1","volume-title":"Rag and rau: A survey on retrieval-augmented language model in natural language processing. arXiv preprint arXiv:2404.19543","author":"Hu Yucheng","year":"2024","unstructured":"Yucheng Hu and Yuxing Lu. 2024. Rag and rau: A survey on retrieval-augmented language model in natural language processing. arXiv preprint arXiv:2404.19543 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models. arXiv preprint arXiv:2404.10981","author":"Huang Yizheng","year":"2024","unstructured":"Yizheng Huang and Jimmy Huang. 2024. A Survey on Retrieval-Augmented Text Generation for Large Language Models. arXiv preprint arXiv:2404.10981 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Nicolas Anciaux, and Joaquin Garcia-Alfaro.","author":"Ibanez-Lissen Luis","year":"2024","unstructured":"Luis Ibanez-Lissen, Lorena Gonzalez-Manzano, Jose Maria de Fuentes, Nicolas Anciaux, and Joaquin Garcia-Alfaro. 2024. LUMIA: Linear probing for Unimodal and MultiModal Membership Inference A! acks leveraging internal LLM states. arXiv preprint arXiv:2411.19876 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Longllmlingua: Accelerating and enhancing llms in long context scenarios via prompt compression. arXiv preprint arXiv:2310.06839","author":"Jiang Huiqiang","year":"2023","unstructured":"Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2023. Longllmlingua: Accelerating and enhancing llms in long context scenarios via prompt compression. arXiv preprint arXiv:2310.06839 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"How large language models encode context knowledge? a layer-wise probing study. arXiv preprint arXiv:2402.16061","author":"Ju Tianjie","year":"2024","unstructured":"Tianjie Ju, Weiwei Sun, Wei Du, Xinwei Yuan, Zhaochun Ren, and Gongshen Liu. 2024. How large language models encode context knowledge? a layer-wise probing study. arXiv preprint arXiv:2402.16061 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"Compressing context to enhance inference efficiency of large language models. arXiv preprint arXiv:2310.06201","author":"Li Yucheng","year":"2023","unstructured":"Yucheng Li, Bo Dong, Chenghua Lin, and Frank Guerin. 2023. Compressing context to enhance inference efficiency of large language models. arXiv preprint arXiv:2310.06201 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Prompt compression for large language models: A survey. arXiv preprint arXiv:2410.12388","author":"Li Zongqian","year":"2024","unstructured":"Zongqian Li, Yinhong Liu, Yixuan Su, and Nigel Collier. 2024. Prompt compression for large language models: A survey. arXiv preprint arXiv:2410.12388 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"500xCompressor: Generalized Prompt Compression for Large Language Models. arXiv preprint arXiv:2408.03094","author":"Li Zongqian","year":"2024","unstructured":"Zongqian Li, Yixuan Su, and Nigel Collier. 2024. 500xCompressor: Generalized Prompt Compression for Large Language Models. arXiv preprint arXiv:2408.03094 (2024)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_2_1_24_1","volume-title":"Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation. arXiv preprint arXiv:2409.15699","author":"Liu Zheng","year":"2024","unstructured":"Zheng Liu, ChenyuanWu, Ninglu Shao, Shitao Xiao, Chaozhuo Li, and Defu Lian. 2024. Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation. arXiv preprint arXiv:2409.15699 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"e_1_3_2_1_26_1","volume-title":"Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, and Ajmal Mian.","author":"Naveed Humza","year":"2023","unstructured":"Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, and Ajmal Mian. 2023. A comprehensive overview of large language models. arXiv preprint arXiv:2307.06435 (2023)."},{"key":"e_1_3_2_1_27_1","unstructured":"Tri Nguyen Mir Rosenberg Xia Song Jianfeng Gao Saurabh Tiwary Rangan Majumder and Li Deng. 2016. Ms marco: A human-generated machine reading comprehension dataset. (2016)."},{"key":"e_1_3_2_1_28_1","unstructured":"Erik Nijkamp Tian Xie Hiroaki Hayashi Bo Pang Congying Xia Chen Xing Jesse Vig Semih Yavuz Philippe Laban Ben Krause et al. 2023. Xgen-7b technical report. arXiv preprint arXiv:2309.03450 (2023)."},{"key":"e_1_3_2_1_29_1","unstructured":"Venkatesh Balavadhani Parthasarathy Ahtsham Zafar Aafaq Khan and Arsalan Shahid. 2024. The ultimate guide to fine-tuning llms from basics to breakthroughs: An exhaustive review of technologies research best practices applied research challenges and opportunities. arXiv preprint arXiv:2408.13296 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Yarn: Efficient context window extension of large language models. arXiv preprint arXiv:2309.00071","author":"Peng Bowen","year":"2023","unstructured":"Bowen Peng, Jeffrey Quesnelle, Honglu Fan, and Enrico Shippole. 2023. Yarn: Efficient context window extension of large language models. arXiv preprint arXiv:2309.00071 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Know what you don't know: Unanswerable questions for SQuAD. arXiv preprint arXiv:1806.03822","author":"Rajpurkar Pranav","year":"2018","unstructured":"Pranav Rajpurkar, Robin Jia, and Percy Liang. 2018. Know what you don't know: Unanswerable questions for SQuAD. arXiv preprint arXiv:1806.03822 (2018)."},{"key":"e_1_3_2_1_32_1","volume-title":"Context embeddings for efficient answer generation in rag. arXiv preprint arXiv:2407.09252","author":"Rau David","year":"2024","unstructured":"David Rau, Shuai Wang, Herv\u00e9 D\u00e9jean, and St\u00e9phane Clinchant. 2024. Context embeddings for efficient answer generation in rag. arXiv preprint arXiv:2407.09252 (2024)."},{"key":"e_1_3_2_1_33_1","unstructured":"Cunxiang Wang Xiaoze Liu Yuanhao Yue Xiangru Tang Tianhang Zhang Cheng Jiayang Yunzhi Yao Wenyang Gao Xuming Hu Zehan Qi et al. 2023. Survey on factuality in large language models: Knowledge retrieval and domainspecificity. arXiv preprint arXiv:2310.07521 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"Probing the Emergence of Cross-lingual Alignment during LLM Training. arXiv preprint arXiv:2406.13229","author":"Wang Hetong","year":"2024","unstructured":"Hetong Wang, Pasquale Minervini, and Edoardo M Ponti. 2024. Probing the Emergence of Cross-lingual Alignment during LLM Training. arXiv preprint arXiv:2406.13229 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Exploring the reasoning abilities of multimodal large language models (mllms): A comprehensive survey on emerging trends in multimodal reasoning. arXiv preprint arXiv:2401.06805","author":"Wang Yiqi","year":"2024","unstructured":"Yiqi Wang, Wentao Chen, Xiaotian Han, Xudong Lin, Haiteng Zhao, Yongfei Liu, Bohan Zhai, Jianbo Yuan, Quanzeng You, and Hongxia Yang. 2024. Exploring the reasoning abilities of multimodal large language models (mllms): A comprehensive survey on emerging trends in multimodal reasoning. arXiv preprint arXiv:2401.06805 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"Evaluating LLMs with Multiple Problems at once: A New Paradigm for Probing LLM Capabilities. arXiv preprint arXiv:2406.10786","author":"Wang Zhengxiang","year":"2024","unstructured":"Zhengxiang Wang, Jordan Kodner, and Owen Rambow. 2024. Evaluating LLMs with Multiple Problems at once: A New Paradigm for Probing LLM Capabilities. arXiv preprint arXiv:2406.10786 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"HotpotQA: A dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600","author":"Yang Zhilin","year":"2018","unstructured":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, WilliamWCohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. HotpotQA: A dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600 (2018)."},{"key":"e_1_3_2_1_38_1","volume-title":"Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473","author":"Zhao Penghao","year":"2024","unstructured":"Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang,Wentao Zhang, and Bin Cui. 2024. Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING","author":"Zhao Yichun","year":"2024","unstructured":"Yichun Zhao, Shuheng Zhou, and Huijia Zhu. 2024. Probe Then Retrieve and Reason: Distilling Probing and Reasoning Capabilities into Smaller Language Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 13026--13032."},{"key":"e_1_3_2_1_40_1","volume-title":"Pose: Efficient context window extension of llms via positional skip-wise training. arXiv preprint arXiv:2309.10400","author":"Zhu Dawei","year":"2023","unstructured":"Dawei Zhu, Nan Yang, Liang Wang, Yifan Song, Wenhao Wu, Furu Wei, and Sujian Li. 2023. Pose: Efficient context window extension of llms via positional skip-wise training. arXiv preprint arXiv:2309.10400 (2023)."}],"event":{"name":"SIGIR-AP 2025:Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","location":"Xi'an China","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region"],"original-title":[],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:16:15Z","timestamp":1764782175000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767695.3769499"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":40,"alternative-id":["10.1145\/3767695.3769499","10.1145\/3767695"],"URL":"https:\/\/doi.org\/10.1145\/3767695.3769499","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}