Kristen Marie Johnson

24 papers A* 2B 2Journal 11Unranked 9

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	A Survey to Recent Progress Towards Understanding In-Context Learning. NAACL (Findings) Haitao Mao, Guangliang Liu, Yao Ma, Rongrong Wang, Kristen Marie Johnson, Jiliang Tang
2025	—	`conf`	Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization. EMNLP (Findings) Guangliang Liu, Zimo Qi, Xitong Zhang, Lei Jiang, Kristen Marie Johnson
2025	J	`jnl`	Diagnosing the Performance Trade-off in Moral Alignment: A Case Study on Gender Stereotypes. CoRR Guangliang Liu, Bocheng Chen, Xitong Zhang, Kristen Marie Johnson
2025	—	`conf`	Discourse Heuristics For Paradoxically Moral Self-Correction. EMNLP (Findings) Guangliang Liu, Zimo Qi, Xitong Zhang, Kristen Marie Johnson
2025	J	`jnl`	Discourse Heuristics For Paradoxically Moral Self-Correction. CoRR Guangliang Liu, Zimo Qi, Xitong Zhang, Kristen Marie Johnson
2025	—	`conf`	Moral Self-correction is Not An Innate Capability in Language Models. IJCNLP-AACL (Findings) Guangliang Liu, Zimo Qi, Xitong Zhang, Lu Cheng, Kristen Marie Johnson
2025	—	`conf`	On the Convergence of Moral Self-Correction in Large Language Models. IJCNLP-AACL (long papers) Guangliang Liu, Haitao Mao, Bochuan Cao, Xitong Zhang, Zhiyu Xue, Rongrong Wang, Kristen Marie Johnson
2025	J	`jnl`	On the Convergence of Moral Self-Correction in Large Language Models. CoRR Guangliang Liu, Haitao Mao, Bochuan Cao, Zhiyu Xue, Xitong Zhang, Rongrong Wang, Kristen Marie Johnson
2025	J	`jnl`	Revealing the Pragmatic Dilemma for Moral Reasoning Acquisition in Language Models. CoRR Guangliang Liu, Lei Jiang, Xitong Zhang, Kristen Marie Johnson
2024	—	`conf`	ABLE: Agency-BeLiefs Embedding to Address Stereotypical Bias through Awareness Instead of Obliviousness. LREC/COLING Michelle YoungJin Kim, Junghwan Kim, Kristen Marie Johnson
2024	A*	`conf`	Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis. EMNLP Guangliang Liu, Haitao Mao, Jiliang Tang, Kristen Marie Johnson
2024	J	`jnl`	Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis. CoRR Guangliang Liu, Haitao Mao, Jiliang Tang, Kristen Marie Johnson
2024	J	`jnl`	Is Moral Self-correction An Innate Capability of Large Language Models? A Mechanistic Analysis to Self-correction. CoRR Zimo Qi, Guangliang Liu, Kristen Marie Johnson, Lu Chen
2024	J	`jnl`	No Free Lunch for Defending Against Prefilling Attack by In-Context Learning. CoRR Zhiyu Xue, Guangliang Liu, Bocheng Chen, Kristen Marie Johnson, Ramtin Pedarsani
2024	J	`jnl`	On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept. CoRR Guangliang Liu, Haitao Mao, Bochuan Cao, Zhiyu Xue, Kristen Marie Johnson, Jiliang Tang, Rongrong Wang
2024	J	`jnl`	Smaller Large Language Models Can Do Moral Self-Correction. CoRR Guangliang Liu, Zhiyu Xue, Rongrong Wang, Kristen Marie Johnson
2024	—	`conf`	Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness. ACL (Findings) Guangliang Liu, Milad Afshari, Xitong Zhang, Zhiyu Xue, Avrajit Ghosh, Bidhan Bashyal, Rongrong Wang, Kristen Marie Johnson
2024	J	`jnl`	Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness. CoRR Guangliang Liu, Milad Afshari, Xitong Zhang, Zhiyu Xue, Avrajit Ghosh, Bidhan Bashyal, Rongrong Wang, Kristen Marie Johnson
2023	A*	`conf`	PAC-tuning: Fine-tuning Pre-trained Language Models with PAC-driven Perturbed Gradient Descent. EMNLP Guangliang Liu, Zhiyu Xue, Xitong Zhang, Kristen Marie Johnson, Rongrong Wang
2023	J	`jnl`	PAC-tuning: Fine-tuning Pretrained Language Models with PAC-driven Perturbed Gradient Descent. CoRR Guangliang Liu, Zhiyu Xue, Xitong Zhang, Kristen Marie Johnson, Rongrong Wang
2023	—	`conf`	Race, Gender, and Age Biases in Biomedical Masked Language Models. ACL (Findings) Michelle Kim, Junghwan Kim, Kristen Marie Johnson
2022	B	`conf`	ASDCLAIMS: Twitter Dataset of Claims on Autism Spectrum Disorder. IEEE Big Data Michelle YoungJin Kim, Junghwan Kim, Bryan Woosung Kim, Kristen Marie Johnson, Jee-In Kim
2022	B	`conf`	CLoSE: Contrastive Learning of Subframe Embeddings for Political Bias Classification of News Media. COLING Michelle YoungJin Kim, Kristen Marie Johnson
2011	—	`conf`	SPATA: A seeding and patching algorithm for de novo transcriptome assembly. BIBM Workshops Zhiyu Zhao, Tin Chi Nguyen, Nan Deng, Kristen Marie Johnson, Dongxiao Zhu