English
Related papers

Related papers: Mechanistic Indicators of Steering Effectiveness i…

200 papers

Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely on binary grammatical contrasts, in this work, we study the…

Computation and Language · Computer Science 2025-09-16 Alina Klerings , Jannik Brinkmann , Daniel Ruffinelli , Simone Ponzetto

Large Language Models (LLMs) have demonstrated their capabilities across various tasks, from language translation to complex reasoning. Understanding and predicting human behavior and biases are crucial for artificial intelligence (AI)…

Artificial Intelligence · Computer Science 2024-08-06 Thuy Ngoc Nguyen , Kasturi Jamale , Cleotilde Gonzalez

While Large Language Models (LLMs) have shown exceptional performance in various tasks, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone. In this paper, we provide evidence that the…

Computation and Language · Computer Science 2023-10-18 Amos Azaria , Tom Mitchell

Recently, Large Language Models (LLMs) have witnessed remarkable performance as zero-shot task planners for robotic manipulation tasks. However, the open-loop nature of previous works makes LLM-based planning error-prone and fragile. On the…

Robotics · Computer Science 2025-03-18 Zhi Zheng , Qian Feng , Hang Li , Alois Knoll , Jianxiang Feng

Large language models (LLMs) have exhibited remarkable capabilities across diverse open-domain tasks, yet their application in specialized domains such as civil engineering remains largely unexplored. This paper starts bridging this gap by…

Computation and Language · Computer Science 2025-07-08 Jiachen Liu , Ziheng Geng , Ran Cao , Lu Cheng , Paolo Bocchini , Minghui Cheng

Human guidance in reinforcement learning (RL) is often impractical for large-scale applications due to high costs and time constraints. Large Language Models (LLMs) offer a promising alternative to mitigate RL sample inefficiency and…

Machine Learning · Computer Science 2024-11-25 Maryam Shoaeinaeini , Brent Harrison

Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in…

Computation and Language · Computer Science 2026-02-03 Jiaqian Li , Yanshu Li , Kuan-Hao Huang

Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited labeled data. While effective, existing methods often apply a fixed steering strength to…

Computation and Language · Computer Science 2026-04-28 Brandon Hsu , Daniel Beaglehole , Adityanarayanan Radhakrishnan , Mikhail Belkin

Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift…

Computation and Language · Computer Science 2025-07-28 Chongyang Tao , Tao Shen , Shen Gao , Junshuo Zhang , Zhen Li , Kai Hua , Wenpeng Hu , Zhengwei Tao , Shuai Ma

We address the challenge of societal bias in Large Language Models (LLMs), focusing on the Llama 2 7B Chat model. As LLMs are increasingly integrated into decision-making processes with substantial societal impact, it becomes imperative to…

Computation and Language · Computer Science 2024-02-02 Dawn Lu , Nina Rimsky

Large language models are increasingly used as behavioral simulators, but it remains unclear when their outputs reflect human-like cognitive mechanisms rather than prompt-sensitive surface patterns. We study this question through the…

Artificial Intelligence · Computer Science 2026-05-26 Ciarán Walsh , Emilio Barkett

Exploratoration and self-observation are key mechanisms of infant sensorimotor development. These processes are further guided by parental scaffolding accelerating skill and knowledge acquisition. In developmental robotics, this approach…

Robotics · Computer Science 2024-01-03 Batuhan Celik , Alper Ahmetoglu , Emre Ugur , Erhan Oztop

Language models (LMs) have been shown to behave unexpectedly post-deployment. For example, new jailbreaks continually arise, allowing model misuse, despite extensive red-teaming and adversarial training from developers. Given most model…

Computation and Language · Computer Science 2024-06-25 Asa Cooper Stickland , Alexander Lyzhov , Jacob Pfau , Salsabila Mahdi , Samuel R. Bowman

There is increasing interest in using LLMs as decision-making "agents." Doing so includes many degrees of freedom: which model should be used; how should it be prompted; should it be asked to introspect, conduct chain-of-thought reasoning,…

Computation and Language · Computer Science 2024-05-29 Narun Raman , Taylor Lundy , Samuel Amouyal , Yoav Levine , Kevin Leyton-Brown , Moshe Tennenholtz

Large Language Models (LLMs) exhibit a troubling duality, capable of both remarkable generalization and brittle, verbatim memorization of their training data. This unpredictability undermines their reliability in high-stakes applications.…

Computation and Language · Computer Science 2025-10-28 Xuanming Zhang

With the significant successes of large language models (LLMs) in many natural language processing tasks, there is growing interest among researchers in exploring LLMs for novel recommender systems. However, we have observed that directly…

Information Retrieval · Computer Science 2023-12-27 Tianhui Ma , Yuan Cheng , Hengshu Zhu , Hui Xiong

Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often uncalibrated inherently and elude conventional calibration techniques due to their…

Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality, pose significant risks. We introduce SteerEval, a…

Computation and Language · Computer Science 2026-04-14 Ziwen Xu , Kewei Xu , Haoming Xu , Haiwen Hong , Longtao Huang , Hui Xue , Ningyu Zhang , Yongliang Shen , Guozhou Zheng , Huajun Chen , Shumin Deng

Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of…

Large Language Models (LLMs) are important tools for reasoning and problem-solving, while they often operate passively, answering questions without actively discovering new ones. This limitation reduces their ability to simulate human-like…

Computational Engineering, Finance, and Science · Computer Science 2025-09-26 Hong Su