English
Related papers

Related papers: Forecasting Rare Language Model Behaviors

200 papers

The recent explosion in the capabilities of large language models has led to a wave of interest in how best to prompt a model to perform a given task. While it may be tempting to simply choose a prompt based on average performance on a…

Machine Learning · Computer Science 2024-03-29 Thomas P. Zollo , Todd Morrill , Zhun Deng , Jake C. Snell , Toniann Pitassi , Richard Zemel

Assessing the capabilities and risks of frontier AI systems is a critical area of research, and recent work has shown that repeated sampling from models can dramatically increase both. For instance, repeated sampling has been shown to…

Artificial Intelligence · Computer Science 2025-10-08 Joshua Kazdan , Rylan Schaeffer , Youssef Allouah , Colin Sullivan , Kyssen Yu , Noam Levi , Sanmi Koyejo

Being probabilistic models, during inference large language models (LLMs) display rare events: behaviour that is far from typical but highly significant. By definition all rare events are hard to see, but the enormous scale of LLM usage…

Machine Learning · Computer Science 2026-05-29 Jake McAllister Dorman , Edward Gillman , Dominic C. Rose , Jamie F. Mair , Juan P. Garrahan

Estimating how often an ML model will fail at deployment scale is central to pre-deployment safety assessment, but a feasible evaluation set is rarely large enough to observe the failures that matter. Jones et al. (2025) address this by…

Machine Learning · Computer Science 2026-05-18 Will Schwarzer , Scott Niekum

Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs,…

Computation and Language · Computer Science 2024-08-06 Yuxia Wang , Zenan Zhai , Haonan Li , Xudong Han , Lizhi Lin , Zhenxuan Zhang , Jingru Zhao , Preslav Nakov , Timothy Baldwin

Language model evaluations often fail to characterize consequential failure modes, forcing experts to inspect outputs and build new benchmarks. We introduce task elicitation, a method that automatically builds new evaluations to profile…

Computation and Language · Computer Science 2025-09-29 Davis Brown , Prithvi Balehannina , Helen Jin , Shreya Havaldar , Hamed Hassani , Eric Wong

Predicting future events is an important activity with applications across multiple fields and domains. For example, the capacity to foresee stock market trends, natural disasters, business developments, or political events can facilitate…

Computation and Language · Computer Science 2025-01-13 Petraq Nako , Adam Jatowt

Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as \emph{evaluation awareness}. This undermines AI safety evaluations, as models may conceal dangerous capabilities during…

Artificial Intelligence · Computer Science 2025-11-11 Maheep Chaudhary , Ian Su , Nikhil Hooda , Nishith Shankar , Julia Tan , Kevin Zhu , Ryan Lagasse , Vasu Sharma , Ashwinee Panda

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…

Computation and Language · Computer Science 2025-06-19 Xinyi Zeng , Yuying Shang , Jiawei Chen , Jingyuan Zhang , Yu Tian

The widespread adoption of large language models (LLMs) makes it important to recognize their strengths and limitations. We argue that in order to develop a holistic understanding of these systems we need to consider the problem that they…

Computation and Language · Computer Science 2023-09-26 R. Thomas McCoy , Shunyu Yao , Dan Friedman , Matthew Hardy , Thomas L. Griffiths

Language Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human…

Computation and Language · Computer Science 2022-02-08 Ethan Perez , Saffron Huang , Francis Song , Trevor Cai , Roman Ring , John Aslanides , Amelia Glaese , Nat McAleese , Geoffrey Irving

Code language models are increasingly adopted for both understanding and generative tasks. Despite their success, these models frequently produce overconfident incorrect predictions and underconfident correct predictions, undermining their…

Software Engineering · Computer Science 2026-05-20 Ravishka Rathnasuriya , Wei Yang

Our intention is to provide a definitive reference on what it would take to safely make use of generative/predictive models in the absence of a solution to the Eliciting Latent Knowledge problem. Furthermore, we believe that large language…

Artificial Intelligence · Computer Science 2023-02-07 Evan Hubinger , Adam Jermyn , Johannes Treutlein , Rubi Hudson , Kate Woolverton

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

Language models exhibit complex, diverse behaviors when prompted with free-form text, making it difficult to characterize the space of possible outputs. We study the problem of behavior elicitation, where the goal is to search for prompts…

Despite their impressive performance, large language models (LLMs) such as ChatGPT are known to pose important risks. One such set of risks arises from misplaced confidence, whether over-confidence or under-confidence, that the models have…

Computation and Language · Computer Science 2024-08-06 Ke Shen , Mayank Kejriwal

When using large language models (LLMs) in high-stakes applications, we need to know when we can trust their predictions. Some works argue that prompting high-performance LLMs is sufficient to produce calibrated uncertainties, while others…

Conversation forecasting tasks a model with predicting the outcome of an unfolding conversation. For instance, it can be applied in social media moderation to predict harmful user behaviors before they occur, allowing for preventative…

Computation and Language · Computer Science 2024-10-22 Anthony Sicilia , Malihe Alikhani

Large language models (LLMs) have recently been applied to forecasting tasks, with some works claiming these systems match or exceed human performance. In this paper, we argue that, as a community, we should be careful about such…

Machine Learning · Computer Science 2025-06-03 Daniel Paleka , Shashwat Goel , Jonas Geiping , Florian Tramèr

In conversational search, agents can interact with users by asking clarifying questions to increase their chance to find better results. Many recent works and shared tasks in both NLP and IR communities have focused on identifying the need…

Information Retrieval · Computer Science 2022-01-04 Zhenduo Wang , Qingyao Ai
‹ Prev 1 2 3 10 Next ›