English
Related papers

Related papers: Prompts have evil twins

200 papers

Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper,…

Computation and Language · Computer Science 2024-12-16 Tom Kouwenhoven , Max Peeperkorn , Tessa Verhoef

Large language models can be prompted to produce text. They can also be prompted to produce "explanations" of their output. But these are not really explanations, because they do not accurately reflect the mechanical process underlying the…

Human-Computer Interaction · Computer Science 2024-05-08 Advait Sarkar

Two languages are considered mutually intelligible if their native speakers can communicate with each other, while using their own mother tongue. How does the fact that humans perceive a language pair as mutually intelligible affect the…

Computation and Language · Computer Science 2022-02-01 Avital Friedland , Jonathan Zeltser , Omer Levy

We lack a systematic understanding of the effects of fine-tuning (via methods such as instruction-tuning or reinforcement learning from human feedback), particularly on tasks outside the narrow fine-tuning distribution. In a simplified…

Computation and Language · Computer Science 2024-04-16 Suhas Kotha , Jacob Mitchell Springer , Aditi Raghunathan

Reward modeling has emerged as a crucial component in aligning large language models with human values. Significant attention has focused on using reward models as a means for fine-tuning generative models. However, the reward models…

Computation and Language · Computer Science 2026-02-04 Brian Christian , Hannah Rose Kirk , Jessica A. F. Thompson , Christopher Summerfield , Tsvetomira Dumbalska

Prompt-based probing has been widely used in evaluating the abilities of pretrained language models (PLMs). Unfortunately, recent studies have discovered such an evaluation may be inaccurate, inconsistent and unreliable. Furthermore, the…

Computation and Language · Computer Science 2022-03-24 Boxi Cao , Hongyu Lin , Xianpei Han , Fangchao Liu , Le Sun

Language models produce a distribution over the next token; can we use this information to recover the prompt tokens? We consider the problem of language model inversion and show that next-token probabilities contain a surprising amount of…

Computation and Language · Computer Science 2023-11-27 John X. Morris , Wenting Zhao , Justin T. Chiu , Vitaly Shmatikov , Alexander M. Rush

Large language models (LLMs) have exploded in popularity in the past few years and have achieved undeniably impressive results on benchmarks as varied as question answering and text summarization. We provide a simple new prompting strategy…

Computation and Language · Computer Science 2022-12-14 Joshua Albrecht , Ellie Kitanidis , Abraham J. Fetterman

Large language models (LLMs) have displayed an impressive ability to harness natural language to perform complex tasks. In this work, we explore whether we can leverage this learned ability to find and explain patterns in data.…

Machine Learning · Computer Science 2023-01-30 Chandan Singh , John X. Morris , Jyoti Aneja , Alexander M. Rush , Jianfeng Gao

Adversarial examples -- inputs with imperceptible perturbations that fool neural networks -- remain one of deep learning's most perplexing phenomena despite nearly a decade of research. While numerous defenses and explanations have been…

Machine Learning · Computer Science 2025-09-16 Liv Gorton , Owen Lewis

This paper investigates false positive constructions: grammatical structures which an LLM hallucinates as distinct constructions but which human introspection does not support. Both a behavioural probing task using contextual embeddings and…

Computation and Language · Computer Science 2025-08-26 Jonathan Dunn , Mai Mohamed Eida

Warning: This paper contains examples of stereotypes and biases. Large Language Models (LLMs) exhibit considerable social biases, and various studies have tried to evaluate and mitigate these biases accurately. Previous studies use…

Computation and Language · Computer Science 2024-07-04 Rem Hida , Masahiro Kaneko , Naoaki Okazaki

Pragmatics and non-literal language understanding are essential to human communication, and present a long-standing challenge for artificial language models. We perform a fine-grained comparison of language models and humans on seven…

Computation and Language · Computer Science 2023-05-25 Jennifer Hu , Sammy Floyd , Olessia Jouravlev , Evelina Fedorenko , Edward Gibson

A frequently observed problem with LLMs is their tendency to generate output that is nonsensical, illogical, or factually incorrect, often referred to broadly as hallucination. Building on the recently proposed HalluciGen task for…

Computation and Language · Computer Science 2025-04-30 Evangelia Gogoulou , Shorouq Zahra , Liane Guillou , Luise Dürlich , Joakim Nivre

The rapid development of large language models (LLMs) gives rise to ethical concerns about their performance, while opening new avenues for developing toxic language detection techniques. However, LLMs' unethical output and their capability…

Computation and Language · Computer Science 2025-08-22 Xi Chen , Shuo Wang

Natural language processing based on large language models (LLMs) is a booming field of AI research. After neural networks have proven to outperform humans in games and practical domains based on pattern recognition, we might stand now at a…

Computers and Society · Computer Science 2023-03-31 Anna Strasser

Discrete optimization-based jailbreaking attacks on large language models aim to generate short, nonsensical suffixes that, when appended onto input prompts, elicit disallowed content. Notably, these suffixes are often transferable --…

Computation and Language · Computer Science 2025-10-28 Sarah Ball , Niki Hasrati , Alexander Robey , Avi Schwarzschild , Frauke Kreuter , Zico Kolter , Andrej Risteski

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

Computation and Language · Computer Science 2024-08-05 Bo Zhou , Daniel Geißler , Paul Lukowicz

The text generated by large language models is commonly controlled by prompting, where a prompt prepended to a user's query guides the model's output. The prompts used by companies to guide their models are often treated as secrets, to be…

Computation and Language · Computer Science 2024-08-09 Yiming Zhang , Nicholas Carlini , Daphne Ippolito

Large language models (LLMs) have achieved top results in recent machine translation evaluations, but they are also known to be sensitive to errors and perturbations in their prompts. We systematically evaluate how both humanly plausible…

Computation and Language · Computer Science 2025-09-03 Patrícia Schmidtová , Niyati Bafna , Seth Aycock , Gianluca Vico , Wiktor Kamzela , Katharina Hämmerl , Vilém Zouhar