--- title: "Beyond Task-Level Context — paper by Zhang et al. (2026)" description: "Implicit in-context learning replaces prompt demonstrations with a context vector added to a model's internal activations. 45 references." authors: ["Jianxin Zhang", "Yilu Hu", "Teng Liu", "Pei Guo", "Juntao Li"] year: 2026 venue: "Findings of the Association for Computational Linguistics: ACL 2026" source: "https://aclanthology.org/2026.findings-acl.1527/" doi: "10.18653/v1/2026.findings-acl.1527" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/zhang-2026-beyond-task-level-context-class/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-beyond-task-level-context-class/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/) / Beyond Task-Level Context: Class-Conditional Context Vectors for Implicit In-Context Learning # Beyond Task-Level Context: Class-Conditional Context Vectors for Implicit In-Context Learning **Authors:** Jianxin Zhang, Yilu Hu, Teng Liu, Pei Guo and [Juntao Li](https://md.research.elamur.ai/free/en/authors/juntao-li/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1527/) · [PDF](https://aclanthology.org/2026.findings-acl.1527.pdf) · [DOI 10.18653/v1/2026.findings-acl.1527](https://doi.org/10.18653/v1/2026.findings-acl.1527) · [OpenAlex](https://openalex.org/W7166817644) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary Implicit in-context learning replaces prompt demonstrations with a context vector added to a model's internal activations. This gives roughly few-shot quality at close to zero-shot cost. Methods such as I2CL, however, average all demonstrations into one task-level vector, which can blur differences between classes. The authors propose C3V (Class-Conditional Context Vectors). C3V groups demonstrations by label and averages attention and MLP activations separately for each class. It then adds all class vectors to the residual stream in one forward pass, weighted by per-layer coefficients. Only these coefficients are learned, using cross-entropy on the same few-shot examples, while the LLM backbone stays frozen. Across nine text classification benchmarks and six LLMs, C3V usually beats task-level context vector baselines. On most models it also exceeds standard few-shot prompting in average accuracy. Representation analyses suggest the gain comes from better separation between classes. The cost is somewhat higher training and inference time, which grows with the number of classes. ## Key points - **Method:** Class coefficients start at 0.1/|C| rather than I2CL's 0.1, which keeps the total injection size comparable. Residual scaling coefficients start at 1. Training uses AdamW (learning rate 1e-2) for 100 epochs. - **Setup:** Five demonstrations per class are sampled from the training set. Each task is tested on 500 examples, and results are averaged over five seeds. - **Ablation:** Macro-average accuracy rises from 58.13% (zero-shot) to 76.32% for full C3V. Variants using noise vectors, frozen coefficients, or 0.1 initialization all score lower, so both coefficient training and initialization matter. - **Efficiency on LLaMA3.2-1B:** - Average inference time is 22.11 s for C3V, 13.60 s for I2CL, and about 69.56 s for uncached few-shot prompting. - The overhead is largest on DBPedia, which has 14 classes. - **Scaling and limitations:** C3V keeps improving as demonstrations per class increase, while standard ICL degrades with longer contexts. The method has been tested only on classification, and its parameter count grows with the size of the label set. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Soochow University](https://md.research.elamur.ai/free/en/universities/soochow-university/) — University, Suzhou, China · 69 works · 4,815 citations 📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works 🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works ## Cite Cite as: Jianxin Zhang, Yilu Hu, Teng Liu, Pei Guo and Juntao Li. 2026. Beyond Task-Level Context: Class-Conditional Context Vectors for Implicit In-Context Learning. Findings of the Association for Computational Linguistics: ACL 2026. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{zhang2026beyond, title = {{Beyond Task-Level Context: Class-Conditional Context Vectors for Implicit In-Context Learning}}, author = {Jianxin Zhang, Yilu Hu, Teng Liu, Pei Guo and Juntao Li}, booktitle = {Findings of the Association for Computational Linguistics: ACL 2026}, year = {2026}, doi = {10.18653/v1/2026.findings-acl.1527}, url = {https://doi.org/10.18653/v1/2026.findings-acl.1527} } ``` - [← previous Beyond Static Toolsets: Self-Evolving LLM Tool Agents via Continual Documentation Adaptation](https://md.research.elamur.ai/free/en/papers/wu-2026-beyond-static-toolsets-self-evolving/) - [next → Beyond the Black Box: Ethical and Theoretical Grounding in Affective Computing](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-beyond-black-box-ethical-theoretical/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/25/) ## References 45 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. AI@Meta. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). 2. Ankush Chatterjee, Kedhar Nath Narahari, Meghana Joshi, and Puneet Agrawal. 2019. [Semeval-2019 task 3: Emocontext contextual emotion detection in text](https://md.research.elamur.ai/free/en/papers/chatterjee-2019-semeval-2019-task-3-emocontext/). In Proceedings of the 13th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT 2019, Minneapolis, MN, USA, June 6-7, 2019, pages 39–48.… 3. Alexis Chevalier, Alexander Wettig, Anirudh Ajith, and Danqi Chen. 2023. [Adapting language models to compress contexts](https://md.research.elamur.ai/free/en/papers/chevalier-2023-adapting-language-models-compress-contexts/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 3829–3846. Association for Computationa… 4. Ona de Gibert, Naiara Pérez, Aitor García-Pablos, and Montse Cuadros. 2018. [Hate speech dataset from a white supremacy forum](https://md.research.elamur.ai/free/en/papers/gibert-2018-hate-speech-dataset-white-supremacy/). In Proceedings of the 2nd Workshop on Abusive Language Online, ALW@EMNLP 2018, Brussels, Belgium, October 31, 2018, pages 11–20. Association for Computational Linguistics. 5. Tao Ge, Jing Hu, Lei Wang, Xun Wang, Si-Qing Chen, and Furu Wei. 2024. [In-context autoencoder for context compression in a large language model](https://md.research.elamur.ai/free/en/papers/ge-2023-context-autoencoder-context-compression-large/). In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. 6. Roee Hendel, Mor Geva, and Amir Globerson. 2023. [In-context learning creates task vectors](https://md.research.elamur.ai/free/en/papers/hendel-2023-context-learning-creates-task-vectors/). In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 9318–9333. Association for Computational Linguistics. 7. Ukyo Honda and Tatsushi Oka. 2025. Exploring explanations improves the robustness of in-context learning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2025, Vienna, Austria, July 27 - August 1, 2025, pages 23693–23714. Associ… [find](https://scholar.google.com/scholar?q=Ukyo+Honda+and+Tatsushi+Oka%2E+2025%2E+Exploring+explanations+improves+the+robustness+of+in%2Dcontext+learning%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Vo) 8. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. 9. Xinyan Hu, Kayo Yin, Michael I. Jordan, Jacob Steinhardt, and Lijie Chen. 2025. Understanding in-context learning of addition via activation subspaces. ArXiv, abs/2505.05145v3. [find](https://scholar.google.com/scholar?q=Xinyan+Hu%2C+Kayo+Yin%2C+Michael+I%2E+Jordan%2C+Jacob+Steinhardt%2C+and+Lijie+Chen%2E+2025%2E+Understanding+in%2Dcontext+learning+of+addition+via+activation+subspaces%2E+ArXiv%2C+abs%2F2505%2E05145v3%2E) 10. Kai Konen, Sophie Jentzsch, Diaoulé Diallo, Peer Schütt, Oliver Bensch, Roxanne El Baff, Dominik Opitz, and Tobias Hecking. 2024. Style vectors for steering generative large language models. In Findings of the Association for Computational Linguistics: EACL 2024, pages 782–802, St. Julian’s, Malta.… [find](https://scholar.google.com/scholar?q=Kai+Konen%2C+Sophie+Jentzsch%2C+Diaoul%C3%A9+Diallo%2C+Peer+Sch%C3%BCtt%2C+Oliver+Bensch%2C+Roxanne+El+Baff%2C+Dominik+Opitz%2C+and+Tobias+Hecking%2E+2024%2E+Style+vectors+for+steering+generative+large+language+models%2E+In+Findin) 11. Vignesh Kothapalli, Hamed Firooz, and Maziar Sanjabi. 2025. Cot-icl lab: A synthetic framework for studying chain-of-thought learning from in-context demonstrations. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2025, Vienna,… [find](https://scholar.google.com/scholar?q=Vignesh+Kothapalli%2C+Hamed+Firooz%2C+and+Maziar+Sanjabi%2E+2025%2E+Cot%2Dicl+lab%3A+A+synthetic+framework+for+studying+chain%2Dof%2Dthought+learning+from+in%2Dcontext+demonstrations%2E+In+Proceedings+of+the+63rd+Annual+) 12. Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. [The power of scale for parameter-efficient prompt tuning](https://md.research.elamur.ai/free/en/papers/lester-2021-power-scale-parameter-efficient-prompt/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021, pages 3045– 3059.… 13. Zhuowei Li, Zihao Xu, Ligong Han, Yunhe Gao, Song Wen, Di Liu, Hao Wang, and Dimitris N. Metaxas. 2025. Implicit in-context learning. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. [find](https://scholar.google.com/scholar?q=Zhuowei+Li%2C+Zihao+Xu%2C+Ligong+Han%2C+Yunhe+Gao%2C+Song+Wen%2C+Di+Liu%2C+Hao+Wang%2C+and+Dimitris+N%2E+Metaxas%2E+2025%2E+Implicit+in%2Dcontext+learning%2E+In+The+Thirteenth+International+Conference+on+Learning+Representat) 14. Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, and Colin Raffel. 2022. [Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning](https://md.research.elamur.ai/free/en/papers/liu-2022-few-shot-parameter-efficient-fine/). In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processin… 15. Hui Liu, Wenya Wang, Hao Sun, Chris Xing Tian, Chenqi Kong, Xin Dong, and Haoliang Li. 2025. [Unraveling the mechanics of learning-based demonstration selection for in-context learning](https://md.research.elamur.ai/free/en/papers/liu-2025-unraveling-mechanics-learning-based-demonstration/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… 16. Sheng Liu, Haotian Ye, Lei Xing, and James Y. Zou. 2024. [In-context vectors: Making in context learning more effective and controllable through latent space steering](https://md.research.elamur.ai/free/en/papers/liu-2023-context-vectors-making-context-learning/). In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. 17. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2019%2E+Decoupled+weight+decay+regularization%2E+In+7th+International+Conference+on+Learning+Representations%2C+ICLR+2019%2C+New+Orleans%2C+LA%2C+USA%2C+May+6%2D9%2C+2019%2E+OpenReview%2En) 18. Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, and Mohit Bansal. 2025. [Multi-attribute steering of language models via targeted intervention](https://md.research.elamur.ai/free/en/papers/nguyen-2025-multi-attribute-steering-language-models/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2025, Vienna, Austria, July 27 - Aug… 19. Bo Pang and Lillian Lee. 2004. [A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts](https://md.research.elamur.ai/free/en/papers/pang-2004-sentimental-education-sentiment-analysis-subjectivity/). In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, 21-26 July, 2004, Barcelona, Spain, pages 271–278. ACL. 20. Bo Pang and Lillian Lee. 2005. [Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales](https://md.research.elamur.ai/free/en/papers/pang-2005-seeing-stars-exploiting-class-relationships/). In ACL 2005, 43rd Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, 25-30 June 2005, University of Michigan, USA, page… 21. Chengwei Qin, Wenhan Xia, Fangkai Jiao, Chen Chen, Yuchen Hu, Bosheng Ding, Ruirui Chen, and Shafiq Joty. 2025. Beyond output matching: Bidirectional alignment for enhanced in-context learning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long… [find](https://scholar.google.com/scholar?q=Chengwei+Qin%2C+Wenhan+Xia%2C+Fangkai+Jiao%2C+Chen+Chen%2C+Yuchen+Hu%2C+Bosheng+Ding%2C+Ruirui+Chen%2C+and+Shafiq+Joty%2E+2025%2E+Beyond+output+matching%3A+Bidirectional+alignment+for+enhanced+in%2Dcontext+learning%2E+In+Pro) 22. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, and 1 others. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+Ilya+Sutskever%2C+and+1+others%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2E) 23. Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, and Alexander Matt Turner. 2024. Steering llama 2 via contrastive activation addition. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand,… [find](https://scholar.google.com/scholar?q=Nina+Rimsky%2C+Nick+Gabrieli%2C+Julian+Schulz%2C+Meg+Tong%2C+Evan+Hubinger%2C+and+Alexander+Matt+Turner%2E+2024%2E+Steering+llama+2+via+contrastive+activation+addition%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+) 24. Baturay Saglam, Xinyang Hu, Zhuoran Yang, Dionysis Kalogerias, and Amin Karbasi. 2025. Learning task representations from in-context learning. In Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27 - August 1, 2025, pages 6634–6663. Association for Computati… [find](https://scholar.google.com/scholar?q=Baturay+Saglam%2C+Xinyang+Hu%2C+Zhuoran+Yang%2C+Dionysis+Kalogerias%2C+and+Amin+Karbasi%2E+2025%2E+Learning+task+representations+from+in%2Dcontext+learning%2E+In+Findings+of+the+Association+for+Computational+Linguist) 25. Daniel Scalena, Gabriele Sarti, and Malvina Nissim. 2024. Multi-property steering of large language models with dynamic activation composition. In Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 577–603, Miami, Florida, US. Association for Compu… [find](https://scholar.google.com/scholar?q=Daniel+Scalena%2C+Gabriele+Sarti%2C+and+Malvina+Nissim%2E+2024%2E+Multi%2Dproperty+steering+of+large+language+models+with+dynamic+activation+composition%2E+In+Proceedings+of+the+7th+BlackboxNLP+Workshop%3A+Analyzin) 26. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Y. Ng, and Christopher Potts. 2013. [Recursive deep models for semantic compositionality over a sentiment treebank](https://md.research.elamur.ai/free/en/papers/socher-2013-recursive-deep-models-semantic-compositionality/). In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 20… 27. Alessandro Stolfo, Vidhisha Balachandran, Safoora Yousefi, Eric Horvitz, and Besmira Nushi. 2025. Improving instruction-following in language models through activation steering. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenRevie… [find](https://scholar.google.com/scholar?q=Alessandro+Stolfo%2C+Vidhisha+Balachandran%2C+Safoora+Yousefi%2C+Eric+Horvitz%2C+and+Besmira+Nushi%2E+2025%2E+Improving+instruction%2Dfollowing+in+language+models+through+activation+steering%2E+In+The+Thirteenth+Inte) 28. Jingran Su, Jingfan Chen, Hongxin Li, Yuntao Chen, Li Qing, and Zhaoxiang Zhang. 2025. [Activation steering decoding: Mitigating hallucination in large vision-language models through bidirectional hidden state intervention](https://md.research.elamur.ai/free/en/papers/su-2025-activation-steering-decoding-mitigating-hallucination/). In Proceedings of the 63rd Annual Meeting of the Association for Computationa… 29. Chenghao Sun, Zhen Huang, Yonggang Zhang, Le Lu, Houqiang Li, Xinmei Tian, Xu Shen, and Jieping Ye. 2025. Interpret and improve in-context learning via the lens of input-label mappings. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)… [find](https://scholar.google.com/scholar?q=Chenghao+Sun%2C+Zhen+Huang%2C+Yonggang+Zhang%2C+Le+Lu%2C+Houqiang+Li%2C+Xinmei+Tian%2C+Xu+Shen%2C+and+Jieping+Ye%2E+2025%2E+Interpret+and+improve+in%2Dcontext+learning+via+the+lens+of+input%2Dlabel+mappings%2E+In+Proceedings) 30. Qwen Team. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388. 31. Eric Todd, Millicent L. Li, Arnab Sen Sharma, Aaron Mueller, Byron C. Wallace, and David Bau. 2024. [Function vectors in large language models](https://md.research.elamur.ai/free/en/papers/todd-2023-function-vectors-large-language-models/). In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. 32. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton-Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, and 49 others… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/) 33. Ellen M. Voorhees and Dawn M. Tice. 2000. Building a question answering test collection. In SIGIR 2000: Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, July 24-28, 2000, Athens, Greece, pages 200–207. ACM. [find](https://scholar.google.com/scholar?q=Ellen+M%2E+Voorhees+and+Dawn+M%2E+Tice%2E+2000%2E+Building+a+question+answering+test+collection%2E+In+SIGIR+2000%3A+Proceedings+of+the+23rd+Annual+International+ACM+SIGIR+Conference+on+Research+and+Development+in) 34. Ben Wang and Aran Komatsuzaki. 2021. Gpt-j-6b: A 6 billion parameter autoregressive language model. [find](https://scholar.google.com/scholar?q=Ben+Wang+and+Aran+Komatsuzaki%2E+2021%2E+Gpt%2Dj%2D6b%3A+A+6+billion+parameter+autoregressive+language+model%2E) 35. Futing Wang, Jianhao Yan, Yue Zhang, and Tao Lin. 2025a. ELICIT: LLM augmentation via external in-context capability. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. [find](https://scholar.google.com/scholar?q=Futing+Wang%2C+Jianhao+Yan%2C+Yue+Zhang%2C+and+Tao+Lin%2E+2025a%2E+ELICIT%3A+LLM+augmentation+via+external+in%2Dcontext+capability%2E+In+The+Thirteenth+International+Conference+on+Learning+Representations%2C+ICLR+2025%2C) 36. Lean Wang, Lei Li, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, and Xu Sun. 2023. [Label words are anchors: An information flow perspective for understanding in-context learning](https://md.research.elamur.ai/free/en/papers/wang-2023-label-words-anchors-information-flow/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapor… 37. Mengru Wang, Ziwen Xu, Shengyu Mao, Shumin Deng, Zhaopeng Tu, Huajun Chen, and Ningyu Zhang. 2025b. [Beyond prompt engineering: Robust behavior control in llms via steering target atoms](https://md.research.elamur.ai/free/en/papers/wang-2025-beyond-prompt-engineering-robust-behavior/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)… 38. Tianyun Yang, Ziniu Li, Juan Cao, and Chang Xu. 2025. Understanding and mitigating hallucination in large vision-language models via modular attribution and intervention. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. [find](https://scholar.google.com/scholar?q=Tianyun+Yang%2C+Ziniu+Li%2C+Juan+Cao%2C+and+Chang+Xu%2E+2025%2E+Understanding+and+mitigating+hallucination+in+large+vision%2Dlanguage+models+via+modular+attribution+and+intervention%2E+In+The+Thirteenth+Internation) 39. Hantao Yao, Rui Zhang, and Changsheng Xu. 2024. TCP: textual-based class-aware prompt tuning for visual-language model. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024, pages 23438–23448. IEEE. [find](https://scholar.google.com/scholar?q=Hantao+Yao%2C+Rui+Zhang%2C+and+Changsheng+Xu%2E+2024%2E+TCP%3A+textual%2Dbased+class%2Daware+prompt+tuning+for+visual%2Dlanguage+model%2E+In+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition%2C+CVPR+2024%2C+Se) 40. Howard Yen, Tianyu Gao, and Danqi Chen. 2024. [Long-context language modeling with parallel context encoding](https://md.research.elamur.ai/free/en/papers/yen-2024-long-context-language-modeling-parallel/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024, pages 2588–2610. Associati… 41. Ashkan Yousefpour, Taeheon Kim, Ryan Sungmo Kwon, Seungbeen Lee, Wonje Jeung, Seungju Han, Alvin Wan, Harrison Ngan, Youngjae Yu, and Jonghyun Choi. 2025. Representation bending for large language model safety. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistic… [find](https://scholar.google.com/scholar?q=Ashkan+Yousefpour%2C+Taeheon+Kim%2C+Ryan+Sungmo+Kwon%2C+Seungbeen+Lee%2C+Wonje+Jeung%2C+Seungju+Han%2C+Alvin+Wan%2C+Harrison+Ngan%2C+Youngjae+Yu%2C+and+Jonghyun+Choi%2E+2025%2E+Representation+bending+for+large+language+mod) 42. Jinghao Zhang, Yuting Liu, Wenjie Wang, Qiang Liu, Shu Wu, Liang Wang, and Tat-Seng Chua. 2025a. [Personalized text generation with contrastive activation steering](https://md.research.elamur.ai/free/en/papers/zhang-2025-personalized-text-generation-contrastive-activation/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2025, Vienna, Au… 43. Xiang Zhang, Junbo Jake Zhao, and Yann LeCun. 2015. [Character-level convolutional networks for text classification](https://md.research.elamur.ai/free/en/papers/zhang-2015-character-level-convolutional-networks-text/). In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, pages 649–657. 44. Zheng Zhang, Shaocheng Lan, Lei Song, Jiang Bian, Yexin Li, and Kan Ren. 2025b. Learning to select in-context demonstration preferred by large language model. In Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27 - August 1, 2025, pages 11345–11360. Associa… [find](https://scholar.google.com/scholar?q=Zheng+Zhang%2C+Shaocheng+Lan%2C+Lei+Song%2C+Jiang+Bian%2C+Yexin+Li%2C+and+Kan+Ren%2E+2025b%2E+Learning+to+select+in%2Dcontext+demonstration+preferred+by+large+language+model%2E+In+Findings+of+the+Association+for+Comput) 45. Yu Zhao, Alessio Devoto, Giwon Hong, Xiaotang Du, Aryo Pradipta Gema, Hongru Wang, Xuanli He, Kam-Fai Wong, and Pasquale Minervini. 2025. Steering knowledge selection behaviours in llms via sae-based representation engineering. In Proceedings of the 2025 Conference of the Nations of the Americas Cha… [find](https://scholar.google.com/scholar?q=Yu+Zhao%2C+Alessio+Devoto%2C+Giwon+Hong%2C+Xiaotang+Du%2C+Aryo+Pradipta+Gema%2C+Hongru+Wang%2C+Xuanli+He%2C+Kam%2DFai+Wong%2C+and+Pasquale+Minervini%2E+2025%2E+Steering+knowledge+selection+behaviours+in+llms+via+sae%2Dbased+) *Updated 2 November 2026*