English
Related papers

Related papers: From Associations to Activations: Comparing Behavi…

200 papers

Synthetic survey data generated by large language models (LLMs) suffers from a fundamental circularity: the same model family that generates text responses also maps them to numerical scales. We calibrate and validate Semantic Similarity…

Physics and Society · Physics 2026-02-24 Eduardo Vera Pichardo

Hedging and non-affirmation are behaviors exhibited by large language models (LLMs) that limit the clear endorsement of specific statements. While these behaviors are desirable in subjective contexts, they are undesirable in the context of…

Large Language Models (LLMs) and Reinforcement Learning (RL) are two powerful approaches for building autonomous agents. However, due to limited understanding of the game environment, agents often resort to inefficient exploration and…

Machine Learning · Computer Science 2024-11-26 Ziyu Chen , Zhiqing Xiao , Xinbei Jiang , Junbo Zhao

Large Language Models (LLMs) have increasingly been utilized in social simulations, where they are often guided by carefully crafted instructions to stably exhibit human-like behaviors during simulations. Nevertheless, we doubt the…

Artificial Intelligence · Computer Science 2024-10-29 Zengqing Wu , Run Peng , Shuyuan Zheng , Qianying Liu , Xu Han , Brian Inhyuk Kwon , Makoto Onizuka , Shaojie Tang , Chuan Xiao

Current benchmarks for Large Language Models (LLMs) primarily focus on performance metrics, often failing to capture the nuanced behavioral characteristics that differentiate them. This paper introduces a novel ``Behavioral Fingerprinting''…

Computation and Language · Computer Science 2025-09-08 Zehua Pei , Hui-Ling Zhen , Ying Zhang , Zhiyuan Yang , Xing Li , Xianzhi Yu , Mingxuan Yuan , Bei Yu

Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been proposed to explain these methods, yet their common goal of…

Machine Learning · Computer Science 2026-03-13 Eric Bigelow , Daniel Wurgaft , YingQiao Wang , Noah Goodman , Tomer Ullman , Hidenori Tanaka , Ekdeep Singh Lubana

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Machine Learning · Computer Science 2024-05-16 Xingzhou Lou , Junge Zhang , Ziyan Wang , Kaiqi Huang , Yali Du

Language model (LM) pre-training is useful in many language processing tasks. But can pre-trained LMs be further leveraged for more general machine learning problems? We propose an approach for using LMs to scaffold learning and…

Power differences shape human communication through well documented socio cognitive effects, including language coordination, pronoun usage, authority bias, and harmful compliance. We examine whether large language models (LLMs) exhibit…

Computation and Language · Computer Science 2026-05-21 Anvesh Rao Vijjini , Sagar Manjunath , Snigdha Chaturvedi

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…

Computation and Language · Computer Science 2025-01-23 Jingyuan Yang , Rongjun Li , Weixuan Wang , Ziyu Zhou , Zhiyong Feng , Wei Peng

We investigate whether Large Language Models (LLMs) exhibit altruistic tendencies, and critically, whether their implicit associations and self-reports predict actual altruistic behavior. Using a multi-method approach inspired by human…

Machine Learning · Computer Science 2025-12-03 Sandro Andric

Recent work has discovered that large language models can develop broadly misaligned behaviors after being fine-tuned on narrowly harmful datasets, a phenomenon known as emergent misalignment (EM). However, the fundamental mechanisms…

Machine Learning · Computer Science 2025-11-05 Daniel Aarao Reis Arturi , Eric Zhang , Andrew Ansah , Kevin Zhu , Ashwinee Panda , Aishwarya Balwani

As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to…

Computation and Language · Computer Science 2024-10-04 Angana Borah , Rada Mihalcea

When encountering increasingly frequent performance improvements or cost reductions from a new large language model (LLM), developers of applications leveraging LLMs must decide whether to take advantage of these improvements or stay with…

Computation and Language · Computer Science 2025-02-20 Rubing Li , João Sedoc , Arun Sundararajan

Large language models (LLMs) have achieved remarkable progress in natural language generation, yet they continue to display puzzling behaviors -- such as repetition and incoherence -- even when exhibiting low perplexity. This highlights a…

Computation and Language · Computer Science 2025-10-27 Xin Du , Kumiko Tanaka-Ishii

Large Language Models (LLMs) exhibit strong reasoning capabilities on structured tasks, yet the internal mechanisms underlying such behaviors remain poorly understood. Existing interpretation methods mainly focus on token-level…

Computation and Language · Computer Science 2026-02-02 Xinnan Dai , Xianxuan Long , Chung-Hsiang Lo , Kai Guo , Shenglai Zeng , Dongsheng Luo , Jiliang Tang

Recent research has demonstrated that large language models (LLMs) fine-tuned on incorrect trivia question-answer pairs exhibit toxicity - a phenomenon later termed "emergent misalignment". Moreover, research has shown that LLMs possess…

Computation and Language · Computer Science 2026-02-17 Laurène Vaugrante , Anietta Weckauff , Thilo Hagendorff

The field of learning analytics has made notable strides in automating the detection of complex learning processes in multimodal data. However, most advancements have focused on individualized problem-solving instead of collaborative,…

We investigate how LLMs encode sociodemographic attributes of human conversational partners inferred from indirect cues such as names and occupations. We show that LLMs develop linear representations of user demographics within activation…

Artificial Intelligence · Computer Science 2025-12-12 Paul Bouchaud , Pedro Ramaciotti

Recent work suggests that LLMs "know what they don't know", positing that hallucinated and factually correct outputs arise from distinct internal processes and can therefore be distinguished using internal signals. However, hallucinations…

Computation and Language · Computer Science 2026-04-20 Chi Seng Cheang , Hou Pong Chan , Wenxuan Zhang , Yang Deng