English
Related papers

Related papers: Split Personality Training: Revealing Latent Knowl…

200 papers

The evaluation and post-training of large language models (LLMs) rely on supervision, but strong supervision for difficult tasks is often unavailable, especially when evaluating frontier models. In such cases, models are demonstrated to…

Machine Learning · Computer Science 2026-01-29 Tianyi Alex Qiu , Micah Carroll , Cameron Allen

Ensuring the safety of large language models (LLMs) is paramount, yet identifying potential vulnerabilities is challenging. While manual red teaming is effective, it is time-consuming, costly and lacks scalability. Automated red teaming…

Cryptography and Security · Computer Science 2024-12-24 Bojian Jiang , Yi Jing , Tianhao Shen , Tong Wu , Qing Yang , Deyi Xiong

Background: The deployment of personalized Large Language Models (LLMs) is currently constrained by the stability-plasticity dilemma. Prevailing alignment methods, such as Supervised Fine-Tuning (SFT), rely on stochastic weight updates that…

Machine Learning · Computer Science 2025-12-09 Zhixiang Wang

Ensuring persona fidelity in large language models (LLMs) is essential for maintaining coherent and engaging human-AI interactions. However, LLMs often exhibit Out-of-Character (OOC) behavior, where generated responses deviate from an…

Computation and Language · Computer Science 2025-06-25 Jisu Shin , Juhyun Oh , Eunsu Kim , Hoyun Song , Alice Oh

Mitigating explicit and implicit biases in Large Language Models (LLMs) has become a critical focus in the field of natural language processing. However, many current methodologies evaluate scenarios in isolation, without considering the…

Computation and Language · Computer Science 2025-02-04 Robert Morabito , Sangmitra Madhusudan , Tyler McDonald , Ali Emami

Recent claims suggest that large language models (LMs) underperform humans in comprehending minimally complex English statements (Dentella et al., 2024). Here, we revisit those findings and argue that human performance was overestimated,…

Computation and Language · Computer Science 2025-05-15 Adele E Goldberg , Supantho Rakshit , Jennifer Hu , Kyle Mahowald

Activation-based probes have emerged as a promising approach for detecting deceptively aligned AI systems by identifying internal conflict between true and stated goals. We identify a fundamental blind spot: probes fail on coherent…

Machine Learning · Computer Science 2026-03-30 Kristiyan Haralambiev

Large Language Models (LLMs) exhibit social biases, which can lead to harmful stereotypes and unfair outcomes. We propose \textbf{Multi-Persona Thinking (MPT)}, a simple inference-time framework that reduces social bias by encouraging…

Computation and Language · Computer Science 2026-04-22 Yuxing Chen , Guoqing Luo , Zijun Wu , Lili Mou

Large Language Models (LLMs) tend to prioritize adherence to user prompts over providing veracious responses, leading to the sycophancy issue. When challenged by users, LLMs tend to admit mistakes and provide inaccurate responses even if…

Computation and Language · Computer Science 2025-02-06 Wei Chen , Zhen Huang , Liang Xie , Binbin Lin , Houqiang Li , Le Lu , Xinmei Tian , Deng Cai , Yonggang Zhang , Wenxiao Wang , Xu Shen , Jieping Ye

Can large language models reliably express a human-like personality, or are they merely mimicking surface cues without a stable underlying profile? To investigate this, we induce personality in LLMs by fine-tuning them on the long-form…

Computation and Language · Computer Science 2026-05-19 Prateek Rajput , Yewei Song , Iyiola E. Olatunji , Jacques Klein , Tegawendé F. Bissyandé

Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they fall short in…

Computation and Language · Computer Science 2025-12-12 Weixiang Zhao , Xingyu Sui , Yulin Hu , Jiahe Guo , Haixiao Liu , Biye Li , Yanyan Zhao , Bing Qin , Ting Liu

As the development and application of Large Language Models (LLMs) continue to advance rapidly, enhancing their trustworthiness and aligning them with human preferences has become a critical area of research. Traditional methods rely…

Computation and Language · Computer Science 2024-11-06 Yuxin Xiao , Chaoqun Wan , Yonggang Zhang , Wenxiao Wang , Binbin Lin , Xiaofei He , Xu Shen , Jieping Ye

Fine-tuning a pretrained language model on a curated dataset can produce spurious correlations between the fine-tuning task and unintended latent factors -- such as misaligned personas or political slant -- that the curation procedure has…

Machine Learning · Statistics 2026-05-28 Ciarán M. Gilligan-Lee , Joseph Egan , Yuchen Zhu , Michael O'Riordan

Large language models (LLMs) rarely admit uncertainty, often producing fluent but misleading answers, rather than abstaining (i.e., refusing to answer). This weakness is even evident in temporal question answering, where models frequently…

Computation and Language · Computer Science 2026-03-05 Xinyu Zhou , Chang Jin , Carsten Eickhoff , Zhijiang Guo , Seyed Ali Bahrainian

Characteristic linguistic behaviors associated with Social Language Disorder (SLD) in autism spectrum disorder, including echoic repetition, pronoun displacement, and stereotyped media quoting, are largely absent from spontaneous…

Computation and Language · Computer Science 2026-05-25 Chuanbo Hu , Minglei Yin , Bin Liu , Wenqi Li , Lynn K. Paul , Shuo Wang , Xin Li

Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time,…

Artificial Intelligence · Computer Science 2024-11-25 Haolin Chen , Yihao Feng , Zuxin Liu , Weiran Yao , Akshara Prabhakar , Shelby Heinecke , Ricky Ho , Phil Mui , Silvio Savarese , Caiming Xiong , Huan Wang

When model developers or users fine-tune an LLM, this can induce behaviors that are unexpected, deliberately harmful, or hard to detect. It would be far easier to audit LLMs if they could simply describe their behaviors in natural language.…

Artificial Intelligence · Computer Science 2026-04-29 Keshav Shenoy , Li Yang , Abhay Sheshadri , Sören Mindermann , Jack Lindsey , Sam Marks , Rowan Wang

Fine-tuning unlocks large language models (LLMs) for specialized applications, but its high computational cost often puts it out of reach for resource-constrained organizations. While cloud platforms could provide the needed resources, data…

Cryptography and Security · Computer Science 2026-04-28 Zihan Liu , Yizhen Wang , Rui Wang , Xiu Tang , Sai Wu

Strategy training is a multidisciplinary rehabilitation approach that teaches skills to reduce disability among those with cognitive impairments following a stroke. Strategy training has been shown in randomized, controlled clinical trials…

Adapting LLMs with new knowledge is increasingly important, but standard fine-tuning often erodes aligned epistemic abstention: the ability to acknowledge when the model does not know. This failure mode is especially concerning in…

Artificial Intelligence · Computer Science 2026-04-22 William F. Shen , Xinchi Qiu , Nicola Cancedda , Nicholas D. Lane