200 citations · 218 across the 14 of their papers we have counts for
14 papers
Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs
Charbel El Feghali, Arkil Patel, Nicholas Meade +3
Open-weight Large Language Models (LLMs) enable scientific progress and broad deployment. However, they make it difficult to control access to sensitive capabilities. Current pract…
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
Xuwei Ding, Skylar Zhai, Linxin Song +6
Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatic…
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
Xing Han Lù, Amirhossein Kazemnejad, Nicholas Meade +7
Web agents enable users to perform tasks on web browsers through natural language interaction. Evaluating web agents trajectories is an important problem, since it helps us determi…
DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
Sara Vera Marjanović, Arkil Patel, Vaibhav Adlakha +14
Large Reasoning Models like DeepSeek-R1 mark a fundamental shift in how LLMs approach complex problems. Instead of directly producing an answer for a given input, DeepSeek-R1 creat…
Exploiting Instruction-Following Retrievers for Malicious Information Retrieval
Parishad BehnamGhader, Nicholas Meade, Siva Reddy
Instruction-following retrievers have been widely adopted alongside LLMs in real-world applications, but little work has investigated the safety risks surrounding their increasing…
SafeArena: Evaluating the Safety of Autonomous Web Agents
Ada Defne Tur, Nicholas Meade, Xing Han Lù +6
LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinf…
Societal Alignment Frameworks Can Improve LLM Alignment
Karolina Stańczak, Nicholas Meade, Mehar Bhatia +14
Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment. However,…
Investigating Adversarial Trigger Transfer in Large Language Models
Nicholas Meade, Arkil Patel, Siva Reddy
Recent work has developed optimization procedures to find token sequences, called adversarial triggers, which can elicit unsafe responses from aligned language models. These trigge…
Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering
Vaibhav Adlakha, Parishad BehnamGhader, Xing Han Lu +2
Retriever-augmented instruction-following models are attractive alternatives to fine-tuned approaches for information-seeking tasks such as question answering (QA). By simply prepe…
StarCoder: may the source be with you!
Raymond Li, Loubna Ben Allal, Yangtian Zi +64
The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase…
Using In-Context Learning to Improve Dialogue Safety
Nicholas Meade, Spandana Gella, Devamanyu Hazarika +5
While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these…
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models
Nicholas Meade, Elinor Poole-Dayan, Siva Reddy
Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques th…
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
Andreas Madsen, Nicholas Meade, Vaibhav Adlakha +1
To explain NLP models a popular approach is to use importance measures, such as attention, which inform input tokens are important for making a prediction. However, an open questio…
Exploring Conditioning for Generative Music Systems with Human-Interpretable Controls
Nicholas Meade, Nicholas Barreyre, Scott C. Lowe +1
Performance RNN is a machine-learning system designed primarily for the generation of solo piano performances using an event-based (rather than audio) representation. More specific…