@misc{niu2025llamaseellamado,
title={Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs},
author={Jingcheng Niu and Xingdi Yuan and Tong Wang and Hamidreza Saghir and Amir H. Abdi},
year={2025},
eprint={2505.09338},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2505.09338},
}
Publications
- 2025Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMsACL 2025
- Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context LearningUnder Review
- 2024ConTempo: A Unified Temporally Contrastive Framework for Temporal Relation ExtractionACL 2024 Findings
- What does the Knowledge Neuron Thesis Have to do with Knowledge?ICLR 2024
(spotlight) - 2023Discourse Information for Document-Level Temporal Dependency ParsingCODI 2023 @ ACL
- 2022Using Roark-Hollingshead Distance to Probe BERT's Syntactic CompetenceBlackBox 2022 @ EMNLP
- Does BERT Rediscover a Classical NLP Pipeline?COLING 2022
(oral) - Chinese Quantifier Scope, Concord, and Lexical Resource SemanticHPSG 2022
- 2021Statistically Evaluating Social Media Sentiment Trends towards COVID-19 Non-Pharmaceutical Interventions with Event StudiesSMM4H 2021 @ NAACL
- 2020Grammaticality and Language ModellingJingcheng Niu and Gerald Penn.Eval4NLP 2020 @ EMNLP
- Temporal Histories of Epidemic Events (THEE): A Case Study in Temporal Annotation for Public HealthLREC 2020
- Artificial intelligence and extracting information from various media sourcesVictoria Ng, Erin E. Rees, Jingcheng Niu, Abdelhamid Zaghlool, Homeira Ghiasbeglou and Adrian Verster.CCDR 2020
- 2019Rationally Reappraising ATIS-based Dialogue SystemsJingcheng Niu and Gerald Penn.ACL 2019