English
Related papers

Related papers: Consistency Training Helps Stop Sycophancy and Jai…

200 papers

With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety alignment, current LLMs remain vulnerable to jailbreaking attacks. However, the root causes…

Artificial Intelligence · Computer Science 2026-03-10 Yonghong Deng , Zhen Yang , Ping Jian , Xinyue Zhang , Zhongbin Guo , Chengzhi Li

When a language model agrees with a user's false belief, is it failing to detect the error, or noticing and agreeing anyway? We show the latter. Across twelve open-weight models from five labs, spanning small to frontier scale, the same…

Machine Learning · Computer Science 2026-05-05 Manav Pandey

Language models are trained to follow instructions, but they are also powerful pattern completers. What happens when these two objectives conflict? We construct conversations in which a user instruction to behave in a target way T (e.g.,…

Computation and Language · Computer Science 2026-05-21 Carolina Camassa , Derek Shiller

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

We propose Consistency-guided Prompt learning (CoPrompt), a new fine-tuning method for vision-language models. Our approach improves the generalization of large foundation models when fine-tuned on downstream tasks in a few-shot setting.…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Shuvendu Roy , Ali Etemad

Large language models excel at many tasks but still struggle with consistent, robust reasoning. We introduce Cohort-based Consistency Learning (CC-Learn), a reinforcement learning framework that improves the reliability of LLM reasoning by…

Computation and Language · Computer Science 2025-06-19 Xiao Ye , Shaswat Shrivastava , Zhaonan Li , Jacob Dineen , Shijie Lu , Avneet Ahuja , Ming Shen , Zhikun Xu , Ben Zhou

Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. While prior research largely attributes this behavior to sycophancy learned during reinforcement learning from human feedback, we…

Computation and Language · Computer Science 2026-05-27 Kevin H. Guo , Chao Yan , Avinash Baidya , Katherine Brown , Xiang Gao , Juming Xiong , Zhijun Yin , Bradley A. Malin

GPT-3 can perform numerous tasks when provided a natural language prompt that contains a few training examples. We show that this type of few-shot learning can be unstable: the choice of prompt format, training examples, and even the order…

Computation and Language · Computer Science 2021-06-14 Tony Z. Zhao , Eric Wallace , Shi Feng , Dan Klein , Sameer Singh

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…

Computation and Language · Computer Science 2026-04-29 Nirmalendu Prakash , Yeo Wei Jie , Amir Abdullah , Ranjan Satapathy , Erik Cambria , Roy Ka Wei Lee

As large language models (LLMs) are adopted in an increasingly wide range of applications, user-model interactions have grown in both frequency and scale. Consequently, research has focused on evaluating the robustness of LLMs, an essential…

Computation and Language · Computer Science 2025-11-17 Jiahang He , Rishi Ramachandran , Neel Ramachandran , Aryan Katakam , Kevin Zhu , Sunishchal Dev , Ashwinee Panda , Aryan Shrivastava

Generative reward models (GRMs) have emerged as a promising approach for aligning Large Language Models (LLMs) with human preferences by offering greater representational capacity and flexibility than traditional scalar reward models.…

Artificial Intelligence · Computer Science 2026-04-21 Yu Liang , Liangxin Liu , Longzheng Wang , Yan Wang , Yueyang Zhang , Long Xia , Zhiyuan Sun , Daiting Shi

Finding the best way of adapting pre-trained language models to a task is a big challenge in current NLP. Just like the previous generation of task-tuned models (TT), models that are adapted to tasks via in-context-learning (ICL) are robust…

Computation and Language · Computer Science 2023-10-23 Lucas Weber , Elia Bruni , Dieuwke Hupkes

We investigate how the presence and type of interaction context shapes sycophancy in LLMs. While real-world interactions allow models to mirror a user's values, preferences, and self-image, prior work often studies sycophancy in zero-shot…

Human-Computer Interaction · Computer Science 2026-02-04 Shomik Jain , Charlotte Park , Matt Viana , Ashia Wilson , Dana Calacci

In order to be deployed safely, Large Language Models (LLMs) must be capable of dynamically adapting their behavior based on their level of knowledge and uncertainty associated with specific topics. This adaptive behavior, which we refer to…

Computation and Language · Computer Science 2024-07-04 Alexandre Piché , Aristides Milios , Dzmitry Bahdanau , Chris Pal

Large language models (LLMs) are often sycophantic, prioritizing agreement with their users over accurate or objective statements. This problematic behavior becomes more pronounced during reinforcement learning from human feedback (RLHF),…

Artificial Intelligence · Computer Science 2024-12-03 Henry Papadatos , Rachel Freedman

Recent works have demonstrated great success in pre-training large-scale autoregressive language models on massive GPUs. To reduce the wall-clock training time, a common practice is to increase the batch size and learning rate. However,…

Machine Learning · Computer Science 2022-10-18 Conglong Li , Minjia Zhang , Yuxiong He

Large language models exhibit sycophancy, the tendency to shift their stated positions toward perceived user preferences or authority cues regardless of evidence. Standard alignment methods fail to correct this because scalar reward models…

Artificial Intelligence · Computer Science 2026-04-08 Muhammad Ahmed Mohsin , Ahsan Bilal , Muhammad Umer , Emily Fox

Instruction tuning -- supervised fine-tuning using instruction-response pairs -- is a key step in making pre-trained large language models (LLMs) instructable. Meanwhile, LLMs perform multitask learning during their pre-training, acquiring…

Computation and Language · Computer Science 2025-09-16 Seokhyun An , Minji Kim , Hyounghun Kim

Fine-tuning large language models is becoming ever more impractical due to their rapidly-growing scale. This motivates the use of parameter-efficient adaptation methods such as prompt tuning (PT), which adds a small number of tunable…

Computation and Language · Computer Science 2023-02-23 Simeng Sun , Yang Liu , Dan Iter , Chenguang Zhu , Mohit Iyyer

Finding appropriate prompts for the specific task has become an important issue as the usage of Large Language Models (LLM) has expanded. Reinforcement Learning (RL) is widely used for prompt tuning, but its inherent instability and…

Computation and Language · Computer Science 2024-10-11 Minchan Kwon , Gaeun Kim , Jongsuk Kim , Haeil Lee , Junmo Kim