English
Related papers

Related papers: Forecasting Rare Language Model Behaviors

200 papers

As large language models (LLMs) are increasingly embedded in everyday decision-making, their safety responsibilities extend beyond reacting to explicit harmful intent toward anticipating unintended but consequential risks. In this work, we…

Computation and Language · Computer Science 2026-02-25 Xuan Luo , Yubin Chen , Zhiyu Hou , Linpu Yu , Geng Tu , Jing Li , Ruifeng Xu

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse

We investigate the predictability of large language model (LLM) capabilities: given records of past experiments using different model families, numbers of parameters, tasks, and numbers of in-context examples, can we accurately predict LLM…

Computation and Language · Computer Science 2023-11-01 Qinyuan Ye , Harvey Yiyun Fu , Xiang Ren , Robin Jia

The current fascination with large language models, or LLMs, derives from the fact that many users lack the expertise to evaluate the quality of the generated text. LLMs may therefore appear more capable than they actually are. The…

Computation and Language · Computer Science 2024-03-15 Eliza Mik

Large-scale surveys are essential tools for informing social science research and policy, but running surveys is costly and time-intensive. If we could accurately simulate group-level survey results, this would therefore be very valuable to…

Computation and Language · Computer Science 2025-02-20 Yong Cao , Haijiang Liu , Arnav Arora , Isabelle Augenstein , Paul Röttger , Daniel Hershcovich

Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…

Computation and Language · Computer Science 2024-05-07 Yuval Reif , Roy Schwartz

Large language models (LLMs) have demonstrated unprecedented emergent capabilities, including content generation, translation, and simulation of human behavior. Field experiments, on the other hand, are widely employed in social studies to…

Computers and Society · Computer Science 2025-05-22 Yaoyu Chen , Yuheng Hu , Yingda Lu

Randomized controlled trials are a cornerstone of medicine and the social sciences as they enable reliable estimates of causal effects. However, they are costly and time-consuming to conduct, motivating interest in predicting causal effects…

Hallucinations are a common issue that undermine the reliability of large language models (LLMs). Recent studies have identified a specific subset of hallucinations, known as confabulations, which arise due to predictive uncertainty of…

Machine Learning · Computer Science 2025-10-24 Mykyta Ielanskyi , Kajetan Schweighofer , Lukas Aichberger , Sepp Hochreiter

Large language models~(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity. To assess the model performance, a typical approach is to construct evaluation benchmarks for…

Computation and Language · Computer Science 2023-11-06 Kun Zhou , Yutao Zhu , Zhipeng Chen , Wentong Chen , Wayne Xin Zhao , Xu Chen , Yankai Lin , Ji-Rong Wen , Jiawei Han

Large language models are rapidly transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis. However, LLM outputs vary significantly depending on the implementation…

Computation and Language · Computer Science 2025-10-07 Joachim Baumann , Paul Röttger , Aleksandra Urman , Albert Wendsjö , Flor Miriam Plaza-del-Arco , Johannes B. Gruber , Dirk Hovy

Large language models offer new ways of empowering people to program robot applications-namely, code generation via prompting. However, the code generated by LLMs is susceptible to errors. This work reports a preliminary exploration that…

Robotics · Computer Science 2023-10-11 Juo-Tung Chen , Chien-Ming Huang

Recent work has investigated the capabilities of large language models (LLMs) as zero-shot models for generating individual-level characteristics (e.g., to serve as risk models or augment survey datasets). However, when should a user have…

Recent advances in language models (LMs) have led to significant improvements in quality on complex NLP tasks, but at the expense of increased inference costs. Cascading offers a simple strategy to achieve more favorable cost-quality…

Computation and Language · Computer Science 2024-04-17 Neha Gupta , Harikrishna Narasimhan , Wittawat Jitkrittum , Ankit Singh Rawat , Aditya Krishna Menon , Sanjiv Kumar

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

Fine-tuning language models is commonly believed to inevitably harm their safety, i.e., refusing to respond to harmful user requests, even when using harmless datasets, thus requiring additional safety measures. We challenge this belief…

Machine Learning · Computer Science 2025-08-19 Minseon Kim , Jin Myung Kwak , Lama Alssum , Bernard Ghanem , Philip Torr , David Krueger , Fazl Barez , Adel Bibi

Web question answering (QA) has become an indispensable component in modern search systems, which can significantly improve users' search experience by providing a direct answer to users' information need. This could be achieved by applying…

Information Retrieval · Computer Science 2019-07-12 Lixin Su , Jiafeng Guo , Yixing Fan , Yanyan Lan , Xueqi Cheng

As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own objectives, a class of risks we term Emergent Strategic Reasoning Risks (ESRRs). These…

Despite the growing demand for eliciting uncertainty from large language models (LLMs), empirical evidence suggests that LLM behavior is not always adequately captured by the elicitation techniques developed under the classical…

Artificial Intelligence · Computer Science 2026-03-12 Anita Yang , Krikamol Muandet , Michele Caprio , Siu Lun Chau , Masaki Adachi

A major risk of using language models in practical applications is their tendency to hallucinate incorrect statements. Hallucinations are often attributed to knowledge gaps in LMs, but we hypothesize that in some cases, when justifying…

Computation and Language · Computer Science 2023-05-24 Muru Zhang , Ofir Press , William Merrill , Alisa Liu , Noah A. Smith