English
Related papers

Related papers: Too Big to Fool: Resisting Deception in Language M…

200 papers

Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker. While recent large language models show remarkable…

Computation and Language · Computer Science 2023-11-14 Etsuko Ishii , Yan Xu , Bryan Wilie , Ziwei Ji , Holy Lovenia , Willy Chung , Pascale Fung

Recent large language models have demonstrated relevant capabilities in solving problems that require logical reasoning; however, the corresponding internal mechanisms remain largely unexplored. In this paper, we show that a small language…

Artificial Intelligence · Computer Science 2025-10-13 Davide Maltoni , Matteo Ferrara

Large Language Models (LLMs) exhibit positional bias, struggling to utilize information from the middle or end of long contexts. Our study explores LLMs' long-context reasoning by probing their hidden representations. We find that while…

Computation and Language · Computer Science 2024-10-08 Taiming Lu , Muhan Gao , Kuai Yu , Adam Byerly , Daniel Khashabi

Large language models (LLMs) increasingly assist software engineering tasks that require reasoning over long code contexts, yet their robustness under varying input conditions remains unclear. We conduct a systematic study of long-context…

Software Engineering · Computer Science 2026-02-20 Kishan Maharaj , Nandakishore Menon , Ashita Saxena , Srikanth Tamilselvam

In-context learning enables large language models (LLMs) to perform a variety of tasks, including learning to make reward-maximizing choices in simple bandit tasks. Given their potential use as (autonomous) decision-making agents, it is…

Computation and Language · Computer Science 2024-05-21 William M. Hayes , Nicolas Yax , Stefano Palminteri

Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relations they are trained on, or fail to make simple logical…

Generative Large Language Models (LLMs) are capable of being in-context learners. However, the underlying mechanism of in-context learning (ICL) is still a major research question, and experimental research results about how models exploit…

Computation and Language · Computer Science 2025-02-11 Aliakbar Nafar , Kristen Brent Venable , Parisa Kordjamshidi

As Large Language Models (LLMs) become increasingly integrated into our daily lives, the potential harms from deceptive behavior underlie the need for faithfully interpreting their decision-making. While traditional probing methods have…

Machine Learning · Computer Science 2024-11-08 Anthony Costarelli , Mat Allen , Severin Field

Showing incorrect answers to Large Language Models (LLMs) is a popular strategy to improve their performance in reasoning-intensive tasks. It is widely assumed that, in order to be helpful, the incorrect answers must be accompanied by…

Computation and Language · Computer Science 2025-09-23 Lisa Alazraki , Maximilian Mozes , Jon Ander Campos , Tan Yi-Chern , Marek Rei , Max Bartolo

Large Language Models (LLMs) have been shown to achieve impressive results for many reasoning-based NLP tasks, suggesting a degree of deductive reasoning capability. However, it remains unclear to which extent LLMs, in both informal and…

Computation and Language · Computer Science 2025-08-26 Fabian Hoppe , Filip Ilievski , Jan-Christoph Kalo

While existing evaluations of large language models (LLMs) measure deception rates, the underlying conditions that give rise to deceptive behavior are poorly understood. We investigate this question using a novel dataset of realistic moral…

By leveraging the retrieval of information from external knowledge databases, Large Language Models (LLMs) exhibit enhanced capabilities for accomplishing many knowledge-intensive tasks. However, due to the inherent flaws of current…

Computation and Language · Computer Science 2024-09-13 Siye Wu , Jian Xie , Jiangjie Chen , Tinghui Zhu , Kai Zhang , Yanghua Xiao

Large Language Models (LLMs) have demonstrated remarkable proficiency across diverse tasks, exhibiting emergent properties such as semantic prompt comprehension, In-Context Learning (ICL), and Chain-of-Thought (CoT) reasoning. Despite their…

Computation and Language · Computer Science 2026-03-13 Yuling Jiao , Yanming Lai , Huazhen Lin , Wensen Ma , Houduo Qi , Defeng Sun

In everyday conversations, humans can take on different roles and adapt their vocabulary to their chosen roles. We explore whether LLMs can take on, that is impersonate, different roles when they generate text in-context. We ask LLMs to…

Artificial Intelligence · Computer Science 2023-11-28 Leonard Salewski , Stephan Alaniz , Isabel Rio-Torto , Eric Schulz , Zeynep Akata

A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight into the underlying cognitive mechanisms. While neural network models trained on large-scale behavioral data often…

Artificial Intelligence · Computer Science 2026-02-03 Jian-Qiao Zhu , Hanbo Xie , Dilip Arumugam , Robert C. Wilson , Thomas L. Griffiths

Language models have the ability to perform in-context learning (ICL), allowing them to flexibly adapt their behavior based on context. This contrasts with in-weights learning (IWL), where memorized information is encoded in model…

Computation and Language · Computer Science 2025-03-04 Suraj Anand , Michael A. Lepori , Jack Merullo , Ellie Pavlick

Despite their impressive capabilities, Large Language Models (LLMs) exhibit unwanted uncertainty, a phenomenon where a model changes a previously correct answer into an incorrect one when re-prompted. This behavior undermines trust and…

Computation and Language · Computer Science 2025-10-28 Tiasa Singha Roy , Ayush Rajesh Jhaveri , Ilias Triantafyllopoulos

Why do language models trained on contradictory data prefer correct answers? In controlled experiments with small transformers (3.5M--86M parameters), we show that this preference tracks the compressibility structure of errors rather than…

Computation and Language · Computer Science 2026-04-07 Konstantin Krestnikov

Human communication is motivated: people speak, write, and create content with a particular communicative intent in mind. As a result, information that large language models (LLMs) and AI agents process is inherently framed by humans'…

Computation and Language · Computer Science 2026-02-03 Addison J. Wu , Ryan Liu , Kerem Oktar , Theodore R. Sumers , Thomas L. Griffiths

Large language models (LMs) are able to in-context learn -- perform a new task via inference alone by conditioning on a few input-label pairs (demonstrations) and making predictions for new inputs. However, there has been little…

Computation and Language · Computer Science 2022-10-21 Sewon Min , Xinxi Lyu , Ari Holtzman , Mikel Artetxe , Mike Lewis , Hannaneh Hajishirzi , Luke Zettlemoyer
‹ Prev 1 3 4 5 6 7 10 Next ›