English
Related papers

Related papers: The Hypocrisy Gap: Quantifying Divergence Between …

200 papers

Large language models (LLMs) have been found to produce hallucinations when the question exceeds their internal knowledge boundaries. A reliable model should have a clear perception of its knowledge boundaries, providing correct answers…

Computation and Language · Computer Science 2024-08-20 Shiyu Ni , Keping Bi , Lulu Yu , Jiafeng Guo

Large language models (LLMs) often exhibit sycophantic behaviors -- such as excessive agreement with or flattery of the user -- but it is unclear whether these behaviors arise from a single mechanism or multiple distinct processes. We…

Computation and Language · Computer Science 2026-03-24 Daniel Vennemeyer , Phan Anh Duong , Tiffany Zhan , Tianyu Jiang

AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while their internal reasoning is misaligned. We thus…

Machine Learning · Computer Science 2025-02-06 Nicholas Goldowsky-Dill , Bilal Chughtai , Stefan Heimersheim , Marius Hobbhahn

Reasoning models frequently agree with incorrect user suggestions -- a behavior known as sycophancy. However, it is unclear where in the reasoning trace this agreement originates and how strong the commitment is. We introduce…

Artificial Intelligence · Computer Science 2026-02-10 Jacek Duszenko

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

Multimodal large language models (MLLMs) have demonstrated extraordinary capabilities in conducting conversations based on image inputs. However, we observe that MLLMs exhibit a pronounced form of visual sycophantic behavior. While similar…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Renjie Pi , Kehao Miao , Li Peihang , Runtao Liu , Jiahui Gao , Jipeng Zhang , Xiaofang Zhou

Large language models (LLMs) exhibit strikingly conflicting behaviors: they can appear steadfastly overconfident in their initial answers whilst at the same time being prone to excessive doubt when challenged. To investigate this apparent…

Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet. We find…

Computation and Language · Computer Science 2024-10-04 Zhenyu Wu , Qingkai Zeng , Zhihan Zhang , Zhaoxuan Tan , Chao Shen , Meng Jiang

Large Language Model (LLM) sycophancy is a growing concern. The current literature has largely examined sycophancy in contexts with clear right and wrong answers, like coding. However, AI is increasingly being used for emotional support and…

Human-Computer Interaction · Computer Science 2026-03-17 Jean Rehani , Victoria Oldemburgo de Mello , Dariya Ovsyannikova , Ashton Anderson , Michael Inzlicht

LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithfulness metrics have critical limitations, typically relying on…

Artificial Intelligence · Computer Science 2026-02-04 Harry Mayne , Justin Singh Kang , Dewi Gould , Kannan Ramchandran , Adam Mahdi , Noah Y. Siegel

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs) by grounding outputs in retrieved evidence, but faithfulness failures, where generations contradict or extend beyond the provided sources, remain a…

Computation and Language · Computer Science 2026-02-12 Guangzhi Xiong , Zhenghao He , Bohan Liu , Sanchit Sinha , Aidong Zhang

Despite recent advancements showcasing the impressive capabilities of Large Language Models (LLMs) in conversational systems, we show that even state-of-the-art LLMs are morally inconsistent in their generations, questioning their…

Computation and Language · Computer Science 2024-03-11 Vamshi Krishna Bonagiri , Sreeram Vennam , Priyanshul Govil , Ponnurangam Kumaraguru , Manas Gaur

Chain-of-thought (CoT) prompting assumes that generated reasoning reflects a model's internal computation. We show this assumption is wrong in a specific, measurable way: models internally detect their own reasoning errors but outwardly…

Computation and Language · Computer Science 2026-05-12 Aojie Yuan , Zhiyuan Julian Su , Haiyue Zhang , Yi Nian , Yue Zhao

Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the…

Computation and Language · Computer Science 2024-03-13 Shiqi Chen , Miao Xiong , Junteng Liu , Zhengxuan Wu , Teng Xiao , Siyang Gao , Junxian He

Fair decisions require ignoring irrelevant, potentially biasing, information. To achieve this, decision-makers need to approximate what decision they would have made had they not known certain facts, such as the gender or race of a job…

Computation and Language · Computer Science 2026-01-22 Brian Christian , Matan Mazor

Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where outputs may be reused as context. In this work, we…

Computation and Language · Computer Science 2026-03-18 Tianyi Zhou , Johanne Medina , Sanjay Chawla

Confidence calibration is essential for making large language models (LLMs) reliable, yet existing training-free methods have been primarily studied under single-answer question answering. In this paper, we show that these methods break…

Computation and Language · Computer Science 2026-02-10 Yuhan Wang , Shiyu Ni , Zhikai Ding , Zihang Zhan , Yuanzi Li , Keping Bi

Recent work shows that Sparse Autoencoders (SAE) applied to large language model (LLM) layers have neurons corresponding to interpretable concepts. These SAE neurons can be modified to align generated outputs, but only towards…

Computation and Language · Computer Science 2025-07-01 Ananya Joshi , Celia Cintas , Skyler Speakman

Large language models (LLMs) achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet often generate unnecessarily long reasoning paths that incur high inference cost. Recent self-consistency-based approaches…

Computation and Language · Computer Science 2026-03-19 Juming Xiong , Kevin Guo , Congning Ni , Chao Yan , Katherine Brown , Avinash Baidya , Xiang Gao , Bradley Malin , Zhijun Yin

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Mateusz Pach , Shyamgopal Karthik , Quentin Bouniot , Serge Belongie , Zeynep Akata
‹ Prev 1 4 5 6 7 8 10 Next ›