6 papers
In-Context Learning as Implicit Policy Gradient
Masahiro Kaneko, Timothy Baldwin
Recent work has shown that large language models (LLMs) can iteratively improve their outputs by incorporating generated samples and their corresponding evaluation scores as in-con…
Beyond the Resumé: A Rubric-Aware Automatic Interview System for Information Elicitation
Harry Stuart, Masahiro Kaneko, Timothy Baldwin
Effective hiring is integral to the success of an organisation, but it is very challenging to find the most suitable candidates because expert evaluation (e.g.\ interviews conducte…
JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks
Masahiro Kaneko, Ayana Niwa, Timothy Baldwin
Fake news undermines societal trust and decision-making across politics, economics, health, and international relations, and in extreme cases threatens human lives and societal saf…
Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization
Masahiro Kaneko, Zeerak Talat, Timothy Baldwin
Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide e…
Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
Masahiro Kaneko, Timothy Baldwin
Adversarial attacks by malicious users that threaten the safety of large language models (LLMs) can be viewed as attempts to infer a target property that is unknown when an ins…
Balanced Multi-Factor In-Context Learning for Multilingual Large Language Models
Masahiro Kaneko, Alham Fikri Aji, Timothy Baldwin
Multilingual large language models (MLLMs) are able to leverage in-context learning (ICL) to achieve high performance by leveraging cross-lingual knowledge transfer without paramet…