Elamur Research⌕
☰
home / papers / 2025 / SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence

SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence

Paper · 2025 · Zhining Liu, Rana Ali Amjad, Ravinarayana Adkathimar et al.

Summary

Supplying a language model with evidence passages, whether retrieved or user-provided, should make its answers better grounded. In practice, models often miss the crucial facts when the context also contains noise or irrelevant material. The authors find that this is not a failure to locate evidence. When generating the first answer token, the deeper attention layers of several LM families already concentrate heavily on the relevant sentences, even when the final answer is wrong.

SelfElicit exploits this signal at inference time and needs no training:

  1. It averages attention per context sentence over the deeper layers.
  2. It keeps sentences whose score is close enough to the top score.
  3. It wraps those sentences in explicit highlight markers and asks the model to answer again using the marked-up context.

Across open-book QA benchmarks covering single-hop and multi-hop reasoning, SelfElicit yields gains of roughly 5.0–11.7% over plain prompting for several model families. It also beats generative evidence extraction while adding very little compute. This makes it a cheap add-on for retrieval-augmented pipelines built on open-weight models.

Key points

  • Evaluation setup: six LMs of varying sizes, including Llama3.1-8B, Mistral-7B, and Qwen2.5 (7B, 32B). Four QA datasets: HotpotQA, NewsQA, TQA, and NQ.
  • Default settings: sentence scores come from the last 50% of layers, which work well consistently. Sentences are split with spaCy. The selection threshold is α = 0.5, relative to the maximum sentence score.
  • Highlighting and cost: selected sentences are wrapped in <start_important> / <end_important> markers. Detecting the evidence requires generating only one extra token.
  • Baselines and robustness:
    • SelfElicit was compared with CoT, FullElicit (the whole context highlighted) and PromptElicit (the LM extracts evidence generatively).
    • Results are fairly stable for α in [0.5, 1].
    • Multi-hop tasks prefer α near 0.5, while NQ does best at α = 1.
  • Limitation: the method needs access to attention scores, so it cannot be applied to proprietary models. The threshold is static, and adapting it dynamically is left for future work.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksComputer Vision and Pattern Recognition · 3,486 worksInformation Systems · 1,730 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,894 works

Cite

Cite as Zhining Liu, Rana Ali Amjad, Ravinarayana Adkathimar, Tianxin Wei and Hanghang Tong. 2025. SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.acl-long.448

@inproceedings{liu2025selfelicit,
  title = {{SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence}},
  author = {Zhining Liu, Rana Ali Amjad, Ravinarayana Adkathimar, Tianxin Wei and Hanghang Tong},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.448},
  url = {https://doi.org/10.18653/v1/2025.acl-long.448}
}

References

96 references, 27 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Mengting Ai, Tianxin Wei, Yifan Chen, Zeming Guo, and Jingrui He. 2023. Mlp fusion: Towards efficient fine-tuning of dense and mixture-of-experts language models. arXiv e-prints, pages arXiv–2307. find
  2. Mengting Ai, Tianxin Wei, Yifan Chen, Zhichen Zeng, Ritchie Zhao, Girish Varatkar, Bita Darvish Rouhani, Xianfeng Tang, Hanghang Tong, and Jingrui He. 2025. Resmoe: Space-efficient compression of mixture of experts llms via residual restoration. arXiv preprint arXiv:2503.06881. — [arXiv:2503.06881](https://arxiv.org/abs/2503.06881) find
  3. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. Self-rag: Learning to retrieve, generate, and critique through self-reflection. arXiv preprint arXiv:2310.11511.
  4. Yikun Ban, Yuchen Yan, Arindam Banerjee, and Jingrui He. 2021. Ee-net: Exploitation-exploration neural networks in contextual bandits. arXiv preprint arXiv:2110.03177. — [arXiv:2110.03177](https://arxiv.org/abs/2110.03177) find
  5. Wenxuan Bao, Tianxin Wei, Haohan Wang, and Jingrui He. 2023. Adaptive test-time personalization for federated learning. Advances in Neural Information Processing Systems, 36:77882–77914. find
  6. Eunice Chan, Zhining Liu, Ruizhong Qiu, Yuheng Zhang, Ross Maciejewski, and Hanghang Tong. 2024. Group fairness via group consensus. In The 2024 ACM Conference on Fairness, Accountability, and Transparency, pages 1788–1808. find
  7. Lingjie Chen, Ruizhong Qiu, Siyu Yuan, Zhining Liu, Tianxin Wei, Hyunsik Yoo, Zhichen Zeng, Deqing Yang, and Hanghang Tong. 2024a. Wapiti: A watermark for finetuned open-source llms. arXiv preprint arXiv:2410.06467. — [arXiv:2410.06467](https://arxiv.org/abs/2410.06467) find
  8. Shiqi Chen, Miao Xiong, Junteng Liu, Zhengxuan Wu, Teng Xiao, Siyang Gao, and Junxian He. 2024b. In-context sharpness as alerts: An inner representation perspective for hallucination mitigation. In Forty-first International Conference on Machine Learning. find
  9. Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James Glass, and Pengcheng He. 2024. Dola: Decoding by contrasting layers improves factuality in large language models. In International Conference on Learning Representations (ICLR).
  10. Florin Cuconasu, Giovanni Trappolini, Federico Siciliano, Simone Filice, Cesare Campagnano, Yoelle Maarek, Nicola Tonellotto, and Fabrizio Silvestri. 2024. The power of noise: Redefining retrieval for rag systems. In Proceedings of the 47th International ACM SIGIR Conference on Research and Developm…
  11. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783.
  12. Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. A survey on rag meeting llms: Towards retrieval-augmented large language models. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 6491– 6501.
  13. Adam Fisch, Alon Talmor, Robin Jia, Minjoon Seo, Eunsol Choi, and Danqi Chen. 2019. find
  14. Mrqa 2019 shared task: Evaluating generalization in reading comprehension. In EMNLP 2019 MRQA Workshop, page 1.
  15. Dongqi Fu, Liri Fang, Zihao Li, Hanghang Tong, Vetle I. Torvik, and Jingrui He. 2024. Parametric graph representations in the era of foundation models: A survey and position. CoRR, abs/2410.12126. — [arXiv:2410.12126](https://arxiv.org/abs/2410.12126) find
  16. 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.
  17. Kai Guo, Xiaofeng Cao, Zhining Liu, and Yi Chang. 2023. Taming over-smoothing representation on heterophilic graphs. Information Sciences, 647:119463. find
  18. Danny Halawi, Jean-Stanislas Denain, and Jacob Steinhardt. 2024. Overthinking the truth: Understanding how language models process false demonstrations. In The Twelfth International Conference on Learning Representations. find
  19. Xinrui He, Tianxin Wei, and Jingrui He. 2023. Robust basket recommendation via noise-tolerated graph contrastive learning. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pages 709–719. find
  20. Matthew Honnibal and Ines Montani. 2017. spacy 2: Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. To appear, 7(1):411–420. find
  21. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. 2023. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. arXiv preprint arXiv:2311.05232.
  22. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. In ACM Computing Surveys.
  23. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023a. Mistral 7b. arXiv preprint arXiv:2310.06825. find
  24. Zhengbao Jiang, Frank F Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023b. Active retrieval augmented generation. In Empirical Methods in Natural Language Processing (EMNLP).
  25. Mandar Joshi, Eunsol Choi, Daniel S Weld, and Luke Zettlemoyer. 2017. Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. In Association for Computational Linguistics (ACL).
  26. Jean Kaddour, Joshua Harris, Maximilian Mozes, Herbie Bradley, Roberta Raileanu, and Robert McHardy. 2023. Challenges and applications of large language models. In arXiv preprint arXiv:2307.10169.
  27. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. Natural…
  28. Yuhong Li, Yingbing Huang, Bowen Yang, Bharat Venkitesh, Acyr Locatelli, Hanchen Ye, Tianle Cai, Patrick Lewis, and Deming Chen. 2024a. Snapkv: Llm knows what you are looking for before generation. arXiv preprint arXiv:2404.14469.
  29. Yunzhe Li, Junting Wang, Hari Sundaram, and Zhining Liu. 2025. A zero-shot generalization framework for llm-driven cross-domain sequential recommendation. arXiv preprint arXiv:2501.19232. — [arXiv:2501.19232](https://arxiv.org/abs/2501.19232) find
  30. Zihao Li, Lecheng Zheng, Bowen Jin, Dongqi Fu, Baoyu Jing, Yikun Ban, Jingrui He, and Jiawei Han. 2024b. Can graph neural networks learn language with extremely weak text supervision? CoRR, abs/2412.08174. find
  31. Xiao Lin, Jian Kang, Weilin Cong, and Hanghang Tong. 2024a. Bemap: Balanced message passing for fair graph neural network. In Learning on Graphs Conference, pages 37–1. PMLR. find
  32. Xiao Lin, Zhining Liu, Dongqi Fu, Ruizhong Qiu, and Hanghang Tong. 2024b. Backtime: Backdoor attacks on multivariate time series forecasting. arXiv preprint arXiv:2410.02195. — [arXiv:2410.02195](https://arxiv.org/abs/2410.02195) find
  33. Lihui Liu, Boxin Du, Yi Ren Fung, Heng Ji, Jiejun Xu, and Hanghang Tong. 2021a. Kompare: A knowledge graph comparative reasoning system. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’21, page 3308–3318, New York, NY, USA. Association for Computing Mach… find
  34. Lihui Liu, Boxin Du, Jiejun Xu, Yinglong Xia, and Hanghang Tong. 2022. Joint knowledge graph completion and question answering. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’22, page 1098–1108, New York, NY, USA. Association for Computing Machinery. find
  35. Lihui Liu, Blaine Hill, Boxin Du, Fei Wang, and Hanghang Tong. 2024a. Conversational question answering with language models generated reformulations over knowledge graph. In Findings of the Association for Computational Linguistics: ACL 2024, pages 839–850, Bangkok, Thailand. Association for Comput… find
  36. Zhining Liu, Wei Cao, Zhifeng Gao, Jiang Bian, Hechang Chen, Yi Chang, and Tie-Yan Liu. 2020a. Self-paced ensemble for highly imbalanced massive data classification. In 2020 IEEE 36th international conference on data engineering (ICDE), pages 841– 852. IEEE. find
  37. Zhining Liu, Jian Kang, Hanghang Tong, and Yi Chang. 2021b. Imbens: Ensemble class-imbalanced learning in python. arXiv preprint arXiv:2111.12776. — [arXiv:2111.12776](https://arxiv.org/abs/2111.12776) find
  38. Zhining Liu, Ruizhong Qiu, Zhichen Zeng, Hyunsik Yoo, David Zhou, Zhe Xu, Yada Zhu, Kommy Welde-mariam, Jingrui He, and Hanghang Tong. 2024b. find
  39. Class-imbalanced graph learning without class rebalancing. In Forty-first International Conference on Machine Learning. find
  40. Zhining Liu, Ruizhong Qiu, Zhichen Zeng, Yada Zhu, Hendrik Hamann, and Hanghang Tong. 2024c. Aim: Attributing, interpreting, mitigating data unfairness. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 2014–2025. find
  41. Zhining Liu, Pengfei Wei, Jing Jiang, Wei Cao, Jiang Bian, and Yi Chang. 2020b. Mesa: boost ensemble imbalanced learning with meta-sampler. Advances in neural information processing systems, 33:14463– 14474. find
  42. OpenAI. 2022. Introducing chatgpt. https://openai.com/blog/chatgpt. ↗
  43. URL OpenAI. 2023. GPT-4 technical report. arXiv preprint arXiv:2303.08774.
  44. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32.
  45. Alexander Peysakhovich and Adam Lerer. 2023. Attention sorting combats recency bias in long context language models. arXiv preprint arXiv:2310.01427. — [arXiv:2310.01427](https://arxiv.org/abs/2310.01427) find
  46. Ruizhong Qiu, Jun-Gi Jang, Xiao Lin, Lihui Liu, and Hanghang Tong. 2024a. TUCKET: A tensor time series data structure for efficient and accurate factor analysis over time ranges. Proceedings of the VLDB Endowment, 17(13). find
  47. Ruizhong Qiu, Zhiqing Sun, and Yiming Yang. 2022. DIMES: A differentiable meta solver for combinatorial optimization problems. In Advances in Neural Information Processing Systems, volume 35, pages 25531–25546. find
  48. Ruizhong Qiu and Hanghang Tong. 2024. Gradient compressed sensing: A query-efficient gradient estimator for high-dimensional zeroth-order optimization. In Proceedings of the 41st International Conference on Machine Learning. find
  49. Ruizhong Qiu, Dingsu Wang, Lei Ying, H Vincent Poor, Yifang Zhang, and Hanghang Tong. 2023. Reconstructing graph diffusion history from a single snapshot. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 1978–1988. find
  50. Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. In-context retrieval-augmented language models. In Association for Computational Linguistics (ACL).
  51. Weijia Shi, Xiaochuang Han, Mike Lewis, Yulia Tsvetkov, Luke Zettlemoyer, and Wen-tau Yih. 2024. Trusting your evidence: Hallucinate less with context-aware decoding. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language…
  52. Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, and Kaheer Suleman. 2017. Newsqa: A machine comprehension dataset.
  53. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, LLion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems (NeurIPS).
  54. Cunxiang Wang, Xiaoze Liu, Yuanhao Yue, Xiangru Tang, Tianhang Zhang, Cheng Jiayang, Yunzhi Yao, Wenyang Gao, Xuming Hu, Zehan Qi, et al. 2023a. Survey on factuality in large language models: Knowledge, retrieval and domain-specificity. In arXiv preprint arXiv:2310.07521.
  55. Zhiruo Wang, Jun Araki, Zhengbao Jiang, Md Rizwan Parvez, and Graham Neubig. 2023b. Learning to filter context for retrieval-augmented generation. arXiv preprint arXiv:2311.08377.
  56. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022a. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837.
  57. Tianxin Wei, Yifan Chen, Xinrui He, and Jingrui He. 2025a. Connecting domains and contrasting samples: A ladder for domain generalization. find
  58. Tianxin Wei, Fuli Feng, Jiawei Chen, Ziwei Wu, Jinfeng Yi, and Xiangnan He. 2021. Model-agnostic counterfactual reasoning for eliminating popularity bias in recommender system. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, pages 1791–1800. find
  59. Ruizhong Qiu, Zhe Xu, Wenxuan Bao, and Hanghang Tong. 2024b. Ask, and it shall be given: On the Turing completeness of prompting. arXiv, 2411.01992. find
  60. Tianxin Wei, Zeming Guo, Yifan Chen, and Jingrui He. 2023. Ntk-approximating mlp fusion for efficient language model fine-tuning. In International Conference on Machine Learning, pages 36821–36838. PMLR. find
  61. Ruizhong Qiu, Weiliang Will Zeng, Hanghang Tong, James Ezick, and Christopher Lott. 2024c. How efficient is LLM-generated code? A rigorous & high-standard benchmark. arXiv, 2406.06647. find
  62. Tianxin Wei and Jingrui He. 2022. Comprehensive fair meta-learned recommender system. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 1989–1999. find
  63. Tianxin Wei, Bowen Jin, Ruirui Li, Hansi Zeng, Zhengyang Wang, Jianhui Sun, Qingyu Yin, Hanqing Lu, Suhang Wang, Jingrui He, et al. 2024a. Towards unified multi-modal personalization: Large vision-language models for generative recommendation and beyond. arXiv preprint arXiv:2403.10667. — [arXiv:2403.10667](https://arxiv.org/abs/2403.10667) find
  64. Tianxin Wei, Ruizhong Qiu, Yifan Chen, Yunzhe Qi, Jiacheng Lin, Wenju Xu, Sreyashi Nag, Ruirui Li, Hanqing Lu, Zhengyang Wang, Chen Luo, Hui Liu, Suhang Wang, Jingrui He, Qi He, and Xianfeng Tang. 2024b. Robust watermarking for diffusion models: A unified multi-dimensional recipe. find
  65. Tianxin Wei, Ziwei Wu, Ruirui Li, Ziniu Hu, Fuli Feng, Xiangnan He, Yizhou Sun, and Wei Wang. 2020. Fast adaptation for cold-start collaborative filtering with meta-learning. In 2020 IEEE International Conference on Data Mining (ICDM), pages 661–670. IEEE. find
  66. Tianxin Wei, Yuning You, Tianlong Chen, Yang Shen, Jingrui He, and Zhangyang Wang. 2022b. Augmentations in hypergraph contrastive learning: Fabricated and generative. Advances in neural information processing systems, 35:1909–1922. find
  67. Zhepei Wei, Wei-Lin Chen, and Yu Meng. 2025b. InstructRAG: Instructing retrieval-augmented generation via self-synthesized rationales. In The Thirteenth International Conference on Learning Representations. find
  68. Zhepei Wei, Wenlin Yao, Yao Liu, Weizhi Zhang, Qin Lu, Liang Qiu, Changlong Yu, Puyang Xu, Chao Zhang, Bing Yin, Hyokun Yun, and Lihong Li. 2025c. Webagent-r1: Training web agents via end-to-end multi-turn reinforcement learning. Preprint, arXiv:2505.16421.
  69. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, et al. 2020. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 conference on empirical methods in natural language p…
  70. Siye Wu, Jian Xie, Jiangjie Chen, Tinghui Zhu, Kai Zhang, and Yanghua Xiao. 2024. How easily do irrelevant inputs skew the responses of large language models? arXiv preprint arXiv:2404.03302. find
  71. Haobo Xu, Yuchen Yan, Dingsu Wang, Zhe Xu, Zhichen Zeng, Tarek F Abdelzaher, Jiawei Han, and Hanghang Tong. Slog: An inductive spectral graph neural network beyond polynomial filter. In Forty-first International Conference on Machine Learning. find
  72. Zhe Xu, Ruizhong Qiu, Yuzhong Chen, Huiyuan Chen, Xiran Fan, Menghai Pan, Zhichen Zeng, Mahashweta Das, and Hanghang Tong. 2024. Discrete-state continuous-time diffusion for graph generation. In Advances in Neural Information Processing Systems, volume 37. find
  73. Yuchen Yan, Yuzhong Chen, Huiyuan Chen, Xiaoting Li, Zhe Xu, Zhichen Zeng, Lihui Liu, Zhining Liu, and Hanghang Tong. 2024a. Thegcn: Temporal heterophilic graph convolutional network. arXiv preprint arXiv:2412.16435. — [arXiv:2412.16435](https://arxiv.org/abs/2412.16435) find
  74. Yuchen Yan, Yuzhong Chen, Huiyuan Chen, Minghua Xu, Mahashweta Das, Hao Yang, and Hanghang Tong. 2023a. From trainable negative depth to edge heterophily in graphs. Advances in Neural Information Processing Systems, 36:70162–70178. find
  75. Yuchen Yan, Yongyi Hu, Qinghai Zhou, Lihui Liu, Zhichen Zeng, Yuzhong Chen, Menghai Pan, Huiyuan Chen, Mahashweta Das, and Hanghang Tong. 2024b. Pacer: Network embedding from positional to structural. In Proceedings of the ACM on Web Conference 2024, pages 2485–2496. find
  76. Yuchen Yan, Yongyi Hu, Qinghai Zhou, Shurang Wu, Dingsu Wang, and Hanghang Tong. 2024c. Topological anonymous walk embedding: A new structural node embedding approach. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, pages 2796–2806. find
  77. Yuchen Yan, Baoyu Jing, Lihui Liu, Ruijie Wang, Jinning Li, Tarek Abdelzaher, and Hanghang Tong. 2023b. Reconciling competing sampling strategies of network embedding. Advances in Neural Information Processing Systems, 36:6844–6861. find
  78. Yuchen Yan, Lihui Liu, Yikun Ban, Baoyu Jing, and Hanghang Tong. 2021. Dynamic knowledge graph alignment. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 4564–4572. find
  79. Yuchen Yan, Qinghai Zhou, Jinning Li, Tarek Abdelzaher, and Hanghang Tong. 2022. Dissecting cross-layer dependency inference on multi-layered interdependent networks. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pages 2341–2351. find
  80. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, et al. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671. find
  81. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answering. In Empirical Methods in Natural Language Processing (EMNLP).
  82. Hangting Ye, Zhining Liu, Wei Cao, Amir M Amiri, Jiang Bian, Yi Chang, Jon D Lurie, Jim Weinstein, and Tie-Yan Liu. 2023. Web-based long-term spine treatment outcome forecasting. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 3082–3092. find
  83. Hyunsik Yoo, SeongKu Kang, Ruizhong Qiu, Charlie Xu, Fei Wang, and Hanghang Tong. 2025a. Embracing plasticity: Balancing stability and plasticity in continual recommender systems. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. find
  84. Hyunsik Yoo, Ruizhong Qiu, Charlie Xu, Fei Wang, and Hanghang Tong. 2025b. Generalizable recommender system during temporal popularity distribution shifts. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. find
  85. Hyunsik Yoo, Zhichen Zeng, Jian Kang, Ruizhong Qiu, David Zhou, Zhining Liu, Fei Wang, Charlie Xu, Eunice Chan, and Hanghang Tong. 2024. Ensuring user-side fairness in dynamic recommender systems. In Proceedings of the ACM on Web Conference 2024, pages 3667–3678. find
  86. Erxin Yu, Jing Li, and Chunpu Xu. 2024. PopALM: Popularity-aligned language models for social media trendy response prediction. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12867–12878. find
  87. Mert Yuksekgonul, Varun Chandrasekaran, Erik Jones, Suriya Gunasekar, Ranjita Naik, Hamid Palangi, Ece Kamar, and Besmira Nushi. 2024. Attention satisfies: A constraint-satisfaction lens on factual errors of language models. In International Conference on Learning Representations (ICLR). find
  88. Zhichen Zeng, Boxin Du, Si Zhang, Yinglong Xia, Zhining Liu, and Hanghang Tong. 2024a. Hierarchical multi-marginal optimal transport for network alignment. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 16660–16668. find
  89. Zhichen Zeng, Ruizhong Qiu, Zhe Xu, Zhining Liu, Yuchen Yan, Tianxin Wei, Lei Ying, Jingrui He, and Hanghang Tong. 2024b. Graph mixup on approximate gromov–wasserstein geodesics. In Forty-first International Conference on Machine Learning. find
  90. Zhichen Zeng, Si Zhang, Yinglong Xia, and Hanghang Tong. 2023a. Parrot: Position-aware regularized optimal transport for network alignment. In Proceedings of the ACM Web Conference 2023, pages 372–382. find
  91. Zhichen Zeng, Ruike Zhu, Yinglong Xia, Hanqing Zeng, and Hanghang Tong. 2023b. Generative graph dictionary learning. In International Conference on Machine Learning, pages 40749–40769. PMLR. find
  92. Yuheng Zhang, Dian Yu, Tao Ge, Linfeng Song, Zhichen Zeng, Haitao Mi, Nan Jiang, and Dong Yu. 2025. Improving llm general preference alignment via optimistic online mirror descent. arXiv preprint arXiv:2502.16852. — [arXiv:2502.16852](https://arxiv.org/abs/2502.16852) find
  93. Zheng Zhao, Emilio Monti, Jens Lehmann, and Haytham Assem. 2024. Enhancing contextual understanding in large language models through contrastive decoding. arXiv preprint arXiv:2405.02750. find
  94. Lecheng Zheng, Baoyu Jing, Zihao Li, Hanghang Tong, and Jingrui He. 2024a. Heterogeneous contrastive learning for foundation models and beyond. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024, Barcelona, Spain, August 25-29, 2024, pages 6666– 6676. A… find
  95. Lecheng Zheng, Baoyu Jing, Zihao Li, Zhichen Zeng, Tianxin Wei, Mengting Ai, Xinrui He, Lihui Liu, Dongqi Fu, Jiaxuan You, Hanghang Tong, and Jingrui He. 2024b. Pyg-ssl: A graph self-supervised learning toolkit. CoRR, abs/2412.21151. — [arXiv:2412.21151](https://arxiv.org/abs/2412.21151) find
  96. Wenxuan Zhou, Sheng Zhang, Hoifung Poon, and Muhao Chen. 2023. Context-faithful prompting for large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14544–14556.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/liu-2025-selfelicit-your-language-model-secretly/