Search Results for author: Aryo Pradipta Gema

Found 14 papers, 10 papers with code

Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs

no code implementations7 Feb 2025 Rohit Saxena, Aryo Pradipta Gema, Pasquale Minervini

Understanding time from visual representations is a fundamental cognitive skill, yet it remains a challenge for multimodal large language models (MLLMs).

DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations

1 code implementation24 Oct 2024 Aryo Pradipta Gema, Chen Jin, Ahmed Abdulaal, Tom Diethe, Philip Teare, Beatrice Alex, Pasquale Minervini, Amrutha Saseendran

Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs by misrepresenting the provided context or incorrectly recalling internal knowledge.

Instruction Following Question Answering +1

Analysing the Residual Stream of Language Models Under Knowledge Conflicts

1 code implementation21 Oct 2024 Yu Zhao, Xiaotang Du, Giwon Hong, Aryo Pradipta Gema, Alessio Devoto, Hongru Wang, Xuanli He, Kam-Fai Wong, Pasquale Minervini

Through probing tasks, we find that LLMs can internally register the signal of knowledge conflict in the residual stream, which can be accurately detected by probing the intermediate model activations.

Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering

1 code implementation21 Oct 2024 Yu Zhao, Alessio Devoto, Giwon Hong, Xiaotang Du, Aryo Pradipta Gema, Hongru Wang, Xuanli He, Kam-Fai Wong, Pasquale Minervini

In this work, we propose \textsc{SpARE}, a \emph{training-free} representation engineering method that uses pre-trained sparse auto-encoders (SAEs) to control the knowledge selection behaviour of LLMs.

Open-Domain Question Answering

CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning

1 code implementation14 Oct 2024 Joshua Ong Jun Leang, Aryo Pradipta Gema, Shay B. Cohen

Mathematical reasoning remains a significant challenge for large language models (LLMs), despite progress in prompting techniques such as Chain-of-Thought (CoT).

Math Mathematical Reasoning +2

A Comparative Study on Patient Language across Therapeutic Domains for Effective Patient Voice Classification in Online Health Discussions

no code implementations23 Jul 2024 Giorgos Lysandrou, Roma English Owen, Vanja Popovic, Grant Le Brun, Aryo Pradipta Gema, Beatrice Alex, Elizabeth A. L. Fairley

However, the abundance of non-patient posts on social media necessitates filtering out such irrelevant content to distinguish the genuine voices of patients, a task we refer to as patient voice classification.

Language Modelling text similarity

Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints

no code implementations28 May 2024 Aryo Pradipta Gema, Chaeeun Lee, Pasquale Minervini, Luke Daines, T. Ian Simpson, Beatrice Alex

The MEDIQA-CORR 2024 shared task aims to assess the ability of Large Language Models (LLMs) to identify and correct medical errors in clinical notes.

Multiple-choice Sentence

Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4

1 code implementation30 Mar 2024 Aryo Pradipta Gema, Giwon Hong, Pasquale Minervini, Luke Daines, Beatrice Alex

The NLI4CT task assesses Natural Language Inference systems in predicting whether hypotheses entail or contradict evidence from Clinical Trial Reports.

In-Context Learning Language Modelling +4

Vaxformer: Antigenicity-controlled Transformer for Vaccine Design Against SARS-CoV-2

1 code implementation18 May 2023 Aryo Pradipta Gema, Michał Kobiela, Achille Fraisse, Ajitha Rajan, Diego A. Oyarzún, Javier Antonio Alfaro

The SARS-CoV-2 pandemic has emphasised the importance of developing a universal vaccine that can protect against current and future variants of the virus.

Language Modeling Protein Language Model

Cannot find the paper you are looking for? You can Submit a new open access paper.