{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:08:06Z","timestamp":1784138886094,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","award":["24.004.022"],"award-info":[{"award-number":["24.004.022"]}]},{"name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","award":["NWA.1389.20.183"],"award-info":[{"award-number":["NWA.1389.20.183"]}]},{"name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","award":["KICH3.LTP.20.006"],"award-info":[{"award-number":["KICH3.LTP.20.006"]}]},{"name":"European Union (UNITE)","award":["No. 101201510"],"award-info":[{"award-number":["No. 101201510"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809891","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"4064-4068","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reward Shaping for Robust Refusal in Small Language Models for Retrieval-Augmented Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5482-664X","authenticated-orcid":false,"given":"Thilina C.","family":"Rajapakse","sequence":"first","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-0202","authenticated-orcid":false,"given":"Maarten","family":"de Rijke","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Marah Abdin Jyoti Aneja Harkirat Behl S\u00e9bastien Bubeck Ronen Eldan Suriya Gunasekar Michael Harrison Russell J. Hewett Mojan Javaheripi Piero Kauffmann James R. Lee Yin Tat Lee Yuanzhi Li Weishung Liu Caio C. T. Mendes Anh Nguyen Eric Price Gustavo de Rosa Olli Saarikivi Adil Salim Shital Shah Xin Wang Rachel Ward Yue Wu Dingli Yu Cyril Zhang and Yi Zhang. 2024. Phi-4 Technical Report. arXiv preprint arXiv:2412.08905 (2024)."},{"key":"e_1_3_2_1_2_1","unstructured":"Loubna Ben Allal Anton Lozhkov Elie Bakouch Gabriel Mart\u00edn Bl\u00e1zquez Guilherme Penedo Lewis Tunstall Andr\u00e9s Marafioti Hynek Kydl\u00edv cek Agust\u00edn Piqueres Lajar\u00edn Vaibhav Srivastav Joshua Lochner Caleb Fahlgren Xuan-Son Nguyen Cl\u00e9mentine Fourrier Ben Burtenshaw Hugo Larcher Haojun Zhao Cyril Zakka Mathieu Morlon Colin Raffel Leandro von Werra and Thomas Wolf. 2025. SmolLM2: When Smol Goes Big - Data-Centric Training of a Small Language Model. arXiv preprint arXiv:2502.02737 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Magda Dubois, Saleh Khalil, Jasmine Balloch, Joshua Au Yeung, and Dominic Pimenta.","author":"Asgari Elham","year":"2025","unstructured":"Elham Asgari, Nina Monta na-Brown, Magda Dubois, Saleh Khalil, Jasmine Balloch, Joshua Au Yeung, and Dominic Pimenta. 2025. A Framework to Assess Clinical Safety and Hallucination Rates of LLMs, for Medical Text Summarisation. npj Digital Medicine, Vol. 8, 1 (2025), 274."},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Machine Learning. PMLR, 2206-2240","author":"Borgeaud Sebastian","year":"2022","unstructured":"Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George Bm Van Den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et al., 2022. Improving Language Models by Retrieving from Trillions of Tokens. In International Conference on Machine Learning. PMLR, 2206-2240."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00370"},{"key":"e_1_3_2_1_6_1","volume-title":"Retrieval Augmented Language Model Pre-Training. In International Conference on Machine Learning. PMLR, 3929-3938","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. Retrieval Augmented Language Model Pre-Training. In International Conference on Machine Learning. PMLR, 3929-3938."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_3_2_1_8_1","first-page":"1","article-title":"Atlas: Few-shot, Learning with Retrieval Augmented Language Models","volume":"24","author":"Izacard Gautier","year":"2023","unstructured":"Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2023. Atlas: Few-shot, Learning with Retrieval Augmented Language Models. Journal of Machine Learning Research, Vol. 24, 251 (2023), 1-43.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1259"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02068-4"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/jpm14121131"},{"key":"e_1_3_2_1_12_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2020. Retrieval-Augmented Generation for Knowledge-Intensive Nlp Tasks. Advances in neural information processing systems Vol. 33 (2020) 9459-9474."},{"key":"e_1_3_2_1_13_1","volume-title":"Bhavani Iyer, Young-Suk Lee, and Avirup Sil.","author":"Li Yulong","year":"2021","unstructured":"Yulong Li, Martin Franz, Md Arafat Sultan, Bhavani Iyer, Young-Suk Lee, and Avirup Sil. 2021. Learning Cross-Lingual IR, from an English Retriever. arXiv preprint arXiv:2112.08185 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.35"},{"key":"e_1_3_2_1_15_1","volume-title":"LLMs. arXiv preprint arXiv:2410.18451","author":"Liu Chris Yuhao","year":"2024","unstructured":"Chris Yuhao Liu, Liang Zeng, Jiacai Liu, Rui Yan, Jujie He, Chaojie Wang, Shuicheng Yan, Yang Liu, and Yahui Zhou. 2024. Skywork-Reward: Bag, of Tricks, for Reward Modeling, in LLMs. arXiv preprint arXiv:2410.18451 (2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_17_1","volume-title":"Rule Based Rewards for Language Model Safety. In The Thirty-Eighth Annual Conference on Neural Information Processing Systems.","author":"Mu Tong","year":"2024","unstructured":"Tong Mu, Alec Helyar, Johannes Heidecke, Joshua Achiam, Andrea Vallone, Ian D Kivlichan, Molly Lin, Alex Beutel, John Schulman, and Lilian Weng. 2024. Rule Based Rewards for Language Model Safety. In The Thirty-Eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_18_1","volume-title":"Question-Answering with Human Feedback. arXiv preprint arXiv:2112.09332","author":"Nakano Reiichiro","year":"2022","unstructured":"Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess, and John Schulman. 2022. WebGPT: Browser-assisted, Question-Answering with Human Feedback. arXiv preprint arXiv:2112.09332 (2022)."},{"key":"e_1_3_2_1_19_1","volume-title":"Reward-RAG: Enhancing RAG, with Reward Driven Supervision. arXiv preprint arXiv:2410.03780","author":"Nguyen Thang","year":"2024","unstructured":"Thang Nguyen, Peter Chin, and Yu-Wing Tai. 2024. Reward-RAG: Enhancing RAG, with Reward Driven Supervision. arXiv preprint arXiv:2410.03780 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models. arXiv preprint arXiv:2502.14302","author":"Pandit Shrey","year":"2025","unstructured":"Shrey Pandit, Jiawei Xu, Junyuan Hong, Zhangyang Wang, Tianlong Chen, Kaidi Xu, and Ying Ding. 2025. MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models. arXiv preprint arXiv:2502.14302 (2025)."},{"key":"e_1_3_2_1_21_1","volume-title":"Manning","author":"Qi Peng","year":"2020","unstructured":"Peng Qi, Haejun Lee, Oghenetegiri ''TG'' Sido, and Christopher D. Manning. 2020. Retrieve, Rerank, Read, Then Iterate: Answering, Open-Domain Questions of Arbitrary Complexity from Text. arXiv preprint arXiv:2010.12527 (2020)."},{"key":"e_1_3_2_1_22_1","volume-title":"Balancing Helpfulness-Safety Trade-off in Large Language Models. arXiv preprint arXiv:2502.11555","author":"Tan Yingshui","year":"2025","unstructured":"Yingshui Tan, Yilei Jiang, Yanshi Li, Jiaheng Liu, Xingyuan Bu, Wenbo Su, Xiangyu Yue, Xiaoyong Zhu, and Bo Zheng. 2025. Equilibrate RLHF: Towards, Balancing Helpfulness-Safety Trade-off in Large Language Models. arXiv preprint arXiv:2502.11555 (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"Efficient Large Language Models: A Survey. arXiv preprint arXiv:2312.03863","author":"Wan Zhongwei","year":"2024","unstructured":"Zhongwei Wan, Xin Wang, Che Liu, Samiul Alam, Yu Zheng, Jiachen Liu, Zhongnan Qu, Shen Yan, Yi Zhu, Quanlu Zhang, Mosharaf Chowdhury, and Mi Zhang. 2024. Efficient Large Language Models: A Survey. arXiv preprint arXiv:2312.03863 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Reinforcement Learning Enhanced LLMs: A Survey. arXiv preprint arXiv:2412.10400","author":"Wang Shuhe","year":"2025","unstructured":"Shuhe Wang, Shengyu Zhang, Jie Zhang, Runyi Hu, Xiaoya Li, Tianwei Zhang, Jiwei Li, Fei Wu, Guoyin Wang, and Eduard Hovy. 2025b. Reinforcement Learning Enhanced LLMs: A Survey. arXiv preprint arXiv:2412.10400 (2025)."},{"key":"e_1_3_2_1_25_1","first-page":"1","article-title":"Empowering Edge Intelligence: A","volume":"57","author":"Wang Xubin","year":"2025","unstructured":"Xubin Wang, Zhiqing Tang, Jianxiong Guo, Tianhui Meng, Chenhao Wang, Tian Wang, and Weijia Jia. 2025a. Empowering Edge Intelligence: A, Comprehensive Survey on on-Device Ai Models. Comput. Surveys, Vol. 57, 9 (2025), 1-39.","journal-title":"Comprehensive Survey on on-Device Ai Models. Comput. Surveys"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_9"},{"key":"e_1_3_2_1_27_1","volume-title":"Llms to Refuse Unknown Questions Using RL, from Knowledge Feedback. arXiv preprint arXiv:2403.18349","author":"Xu Hongshen","year":"2024","unstructured":"Hongshen Xu, Zichen Zhu, Situo Zhang, Da Ma, Shuai Fan, Lu Chen, and Kai Yu. 2024b. Rejection Improves Reliability: Training, Llms to Refuse Unknown Questions Using RL, from Knowledge Feedback. arXiv preprint arXiv:2403.18349 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"On-Device Language Models: A Comprehensive Review. arXiv preprint arXiv:2409.00088","author":"Xu Jiajun","year":"2024","unstructured":"Jiajun Xu, Zhiyuan Li, Wei Chen, Qun Wang, Xin Gao, Qi Cai, and Ziyuan Ling. 2024a. On-Device Language Models: A Comprehensive Review. arXiv preprint arXiv:2409.00088 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"RAG-reward: Optimizing RAG, with Reward Modeling and RLHF. arXiv preprint arXiv:2501.13264","author":"Zhang Hanning","year":"2025","unstructured":"Hanning Zhang, Juntong Song, Juno Zhu, Yuanhao Wu, Tong Zhang, and Cheng Niu. 2025. RAG-reward: Optimizing RAG, with Reward Modeling and RLHF. arXiv preprint arXiv:2501.13264 (2025)."},{"key":"e_1_3_2_1_30_1","volume-title":"TinyLlama: An Open-Source Small Language Model. arXiv preprint arXiv:2401.02385","author":"Zhang Peiyuan","year":"2024","unstructured":"Peiyuan Zhang, Guangtao Zeng, Tianduo Wang, and Wei Lu. 2024. TinyLlama: An Open-Source Small Language Model. arXiv preprint arXiv:2401.02385 (2024)."},{"key":"e_1_3_2_1_31_1","volume-title":"Fine-Tuning Language Models, from Human Preferences. arXiv preprint arXiv:1909.08593","author":"Ziegler Daniel M.","year":"2020","unstructured":"Daniel M. Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B. Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. 2020. Fine-Tuning Language Models, from Human Preferences. arXiv preprint arXiv:1909.08593 (2020)."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:28:27Z","timestamp":1784136507000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809891"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":31,"alternative-id":["10.1145\/3805712.3809891","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809891","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}