6 citations · 7 across the 10 of their papers we have counts for
10 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…
A Little Leak Will Sink a Great Ship: Survey of Transparency for Large Language Models from Start to Finish
Masahiro Kaneko, Timothy Baldwin
Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Suc…
Eagle: Ethical Dataset Given from Real Interactions
Masahiro Kaneko, Danushka Bollegala, Timothy Baldwin
Recent studies have demonstrated that large language models (LLMs) have ethical-related problems such as social biases, lack of moral reasoning, and generation of offensive content…
Evaluating Gender Bias in Large Language Models via Chain-of-Thought Prompting
Masahiro Kaneko, Danushka Bollegala, Naoaki Okazaki +1
There exist both scalable tasks, like reading comprehension and fact-checking, where model performance improves with model size, and unscalable tasks, like arithmetic reasoning and…
The Gaps between Pre-train and Downstream Settings in Bias Evaluation and Debiasing
Masahiro Kaneko, Danushka Bollegala, Timothy Baldwin
The output tendencies of Pre-trained Language Models (PLM) vary markedly before and after Fine-Tuning (FT) due to the updates to the model parameters. These divergences in output t…