English
Related papers

Related papers: Prompts have evil twins

200 papers

We introduce and study artificial impressions--patterns in LLMs' internal representations of prompts that resemble human impressions and stereotypes based on language. We fit linear probes on generated prompts to predict impressions…

Computation and Language · Computer Science 2025-10-13 Nicholas Deas , Kathleen McKeown

Neural network language models can serve as computational hypotheses about how humans process language. We compared the model-human consistency of diverse language models using a novel experimental approach: controversial sentence pairs.…

Computation and Language · Computer Science 2023-09-15 Tal Golan , Matthew Siegelman , Nikolaus Kriegeskorte , Christopher Baldassano

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Computation and Language · Computer Science 2024-09-04 Bocheng Chen , Hanqing Guo , Guangjing Wang , Yuanda Wang , Qiben Yan

Soft prompts have been popularized as a cheap and easy way to improve task-specific LLM performance beyond few-shot prompts. Despite their origin as an automated prompting method, however, soft prompts and other trainable prompts remain a…

Machine Learning · Computer Science 2025-04-04 Oam Patel , Jason Wang , Nikhil Shivakumar Nayak , Suraj Srinivas , Himabindu Lakkaraju

Do language models (LMs) offer insights into human language learning? A common argument against this idea is that because their architecture and training paradigm are so vastly different from humans, LMs can learn arbitrary inputs as easily…

Computation and Language · Computer Science 2025-09-24 Xiulin Yang , Tatsuya Aoyama , Yuekun Yao , Ethan Wilcox

Modern language models (LMs) are not robust to out-of-distribution inputs. Machine generated (``optimized'') prompts can be used to modulate LM outputs and induce specific behaviors while appearing completely uninterpretable. In this work,…

Computation and Language · Computer Science 2025-09-04 Rimon Melamed , Lucas H. McCabe , H. Howie Huang

According to Futrell and Mahowald [arXiv:2501.17047], both infants and language models (LMs) find attested languages easier to learn than impossible languages that have unnatural structures. We review the literature and show that LMs often…

Computation and Language · Computer Science 2025-11-17 Jeffrey S. Bowers , Jeff Mitchell

Fine-tuning continuous prompts for target tasks has recently emerged as a compact alternative to full model fine-tuning. Motivated by these promising results, we investigate the feasibility of extracting a discrete (textual) interpretation…

Machine-learned language models have transformed everyday life: they steer us when we study, drive, manage money. They have the potential to transform our civilization. But they hallucinate. Their realities are virtual. This note provides a…

Computation and Language · Computer Science 2024-05-24 Dusko Pavlovic

Surprisal theory posits that the processing difficulty of a word is determined by its predictability in context, offering a potential link between human sentence processing and next-word predictions from language models. While language…

Computation and Language · Computer Science 2026-05-18 William Timkey , Brian Dillon , Tal Linzen

A controversial test for Large Language Models concerns the ability to discern possible from impossible language. While some evidence attests to the models' sensitivity to what crosses the limits of grammatically impossible language, this…

Computation and Language · Computer Science 2025-09-19 Evelina Leivada , Raquel Montero , Paolo Morosi , Natalia Moskvina , Tamara Serrano , Marcel Aguilar , Fritz Guenther

System prompts that include detailed instructions to describe the task performed by the underlying LLM can easily transform foundation models into tools and services with minimal overhead. They are often considered intellectual property,…

Cryptography and Security · Computer Science 2025-08-07 David Pape , Sina Mavali , Thorsten Eisenhofer , Lea Schönherr

Prompting is the primary method by which we study and control large language models. It is also one of the most powerful: nearly every major capability attributed to LLMs-few-shot learning, chain-of-thought, constitutional AI-was first…

Computation and Language · Computer Science 2025-07-08 Ari Holtzman , Chenhao Tan

Interaction with Large Language Models (LLMs) is primarily carried out via prompting. A prompt is a natural language instruction designed to elicit certain behaviour or output from a model. In theory, natural language prompts enable…

Human-Computer Interaction · Computer Science 2024-03-15 Michael Desmond , Michelle Brachman

Homonyms are words with identical spelling but distinct meanings, which pose challenges for many generative models. When a homonym appears in a prompt, diffusion models may generate multiple senses of the word simultaneously, which is known…

Computation and Language · Computer Science 2025-09-30 Evgeny Kaskov , Elizaveta Petrova , Petr Surovtsev , Anna Kostikova , Ilya Mistiurin , Alexander Kapitanov , Alexander Nagaev

Prompt sensitivity, referring to the phenomenon where paraphrasing (i.e., repeating something written or spoken using different words) leads to significant changes in large language model (LLM) performance, has been widely accepted as a…

Computation and Language · Computer Science 2025-09-03 Andong Hua , Kenan Tang , Chenhe Gu , Jindong Gu , Eric Wong , Yao Qin

The ever-growing size of the foundation language model has brought significant performance gains in various types of downstream tasks. With the existence of side-effects brought about by the large size of the foundation language model such…

Computation and Language · Computer Science 2022-10-14 Zhengqi He , Taro Toyoizumi

We study whether automatically-induced prompts that effectively extract information from a language model can also be used, out-of-the-box, to probe other language models for the same information. After confirming that discrete prompts…

Computation and Language · Computer Science 2023-03-08 Nathanaël Carraz Rakotonirina , Roberto Dessì , Fabio Petroni , Sebastian Riedel , Marco Baroni

We argue that language models (LMs) have strong potential as investigative tools for probing the distinction between possible and impossible natural languages and thus uncovering the inductive biases that support human language learning. We…

Computation and Language · Computer Science 2025-12-11 Julie Kallini , Christopher Potts

Ambiguity is an intrinsic feature of natural language. Managing ambiguity is a key part of human language understanding, allowing us to anticipate misunderstanding as communicators and revise our interpretations as listeners. As language…

Computation and Language · Computer Science 2023-10-23 Alisa Liu , Zhaofeng Wu , Julian Michael , Alane Suhr , Peter West , Alexander Koller , Swabha Swayamdipta , Noah A. Smith , Yejin Choi