no code implementations • WNUT (ACL) 2021 • Thomas Clark, Costanza Conforti, Fangyu Liu, Zaiqiao Meng, Ehsan Shareghi, Nigel Collier
Stance detection (SD) entails classifying the sentiment of a text towards a given target, and is a relevant sub-task for opinion mining and social media analysis.
1 code implementation • ACL 2022 • Dongwon Ryu, Ehsan Shareghi, Meng Fang, Yunqiu Xu, Shirui Pan, Reza Haf
Text-based games (TGs) are exciting testbeds for developing deep reinforcement learning techniques due to their partially observed environments and large action spaces.
1 code implementation • ACL 2022 • Lan Zhang, Wray Buntine, Ehsan Shareghi
Injecting desired geometric properties into text representations has attracted a lot of attention.
no code implementations • 1 Apr 2025 • Jiuzhou Han, Wray Buntine, Ehsan Shareghi
Large language models demonstrate remarkable reasoning capabilities but often produce unreliable or incorrect responses.
1 code implementation • 31 Mar 2025 • Minghan Wang, Ye Bai, Yuxia Wang, Thuy-Trang Vu, Ehsan Shareghi, Gholamreza Haffari
High-quality speech dialogue datasets are crucial for Speech-LLM development, yet existing acquisition methods face significant limitations.
1 code implementation • 6 Mar 2025 • Zongqian Li, Ehsan Shareghi, Nigel Collier
Large Language Models (LLMs) reasoning processes are challenging to analyze due to their complexity and the lack of organized visualization tools.
1 code implementation • 15 Jan 2025 • Ramya Keerthy Thatikonda, Wray Buntine, Ehsan Shareghi
Using ground-truth FOLs, we carefully designed various perturbations on the ground-truth to assess metric sensitivity.
no code implementations • 9 Dec 2024 • Ehsan Shareghi, Jiuzhou Han, Paul Burgess
In recent years, Large Language Models (LLMs) have shown great potential across a wide range of legal tasks.
1 code implementation • 13 Nov 2024 • Minh Nguyen, Ehsan Shareghi
We introduce STEP, a novel framework designed to efficiently learn from previous experiences to enhance the planning capabilities of language agents in future steps.
1 code implementation • 31 Oct 2024 • Hao Yang, Lizhen Qu, Ehsan Shareghi, Gholamreza Haffari
Our results under these settings demonstrate that open-source audio LMMs suffer an average attack success rate of 69. 14% on harmful audio questions, and exhibit safety vulnerabilities when distracted with non-speech audio noise.
1 code implementation • 15 Oct 2024 • Hao Yang, Lizhen Qu, Ehsan Shareghi, Gholamreza Haffari
Moreover, JSP achieves a state-of-the-art attack success rate of 92% on GPT-4 on the harmful query benchmark, and exhibits strong resistant to defence strategies.
no code implementations • 3 Oct 2024 • Yinhong Liu, Zhijiang Guo, Tianya Liang, Ehsan Shareghi, Ivan Vulić, Nigel Collier
Large Language Models (LLMs) are expected to be predictable and trustworthy to support reliable decision-making systems.
1 code implementation • 24 Sep 2024 • Ramya Keerthy Thatikonda, Jiuzhou Han, Wray Buntine, Ehsan Shareghi
Research in symbolic logical reasoning explored FOL generation using state-of-the-art LLMs (i. e., GPT-4) to produce FOL translations of natural language (NL) statements, but errors in translation are usually not the focus.
1 code implementation • 2 Sep 2024 • Yuan Yang, Siheng Xiong, Ehsan Shareghi, Faramarz Fekri
Recent advancements in large language models (LLMs) have significantly enhanced their capacity to aggregate and process information across multiple modalities, enabling them to perform a wide range of tasks such as multimodal data querying, tool usage, web interactions, and handling long documents.
1 code implementation • 25 Jun 2024 • Hao Yang, Lizhen Qu, Ehsan Shareghi, Gholamreza Haffari
Based on the taxonomy, we create a small-scale dataset for evaluating current LMMs capability in detecting these categories of risk.
1 code implementation • 19 Jun 2024 • Yuan Yang, Siheng Xiong, Ali Payani, Ehsan Shareghi, Faramarz Fekri
To investigate this, we introduce the task of reasoning in the wild, where an LLM is tasked to solve a reasoning problem of unknown type by identifying the subproblems and their corresponding formalisms, and writing a program to solve each subproblem, guided by a tactic.
1 code implementation • 16 Jun 2024 • Minghan Wang, Yuxia Wang, Thuy-Trang Vu, Ehsan Shareghi, Gholamreza Haffari
Recent advancements in multimodal large language models (MLLMs) have made significant progress in integrating information across various modalities, yet real-world applications in educational and scientific domains remain challenging.
1 code implementation • 1 Jun 2024 • Long Hei Matthew Lam, Ramya Keerthy Thatikonda, Ehsan Shareghi
This paradigm has established the current state-of-the-art result in logical reasoning (i. e., deductive reasoning).
1 code implementation • 25 Mar 2024 • Yinhong Liu, Han Zhou, Zhijiang Guo, Ehsan Shareghi, Ivan Vulić, Anna Korhonen, Nigel Collier
Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language.
no code implementations • 22 Feb 2024 • Mahsa Salehi, Kalin Stefanov, Ehsan Shareghi
In this paper we study the variations in human brain activity when listening to real and fake audio.
no code implementations • 16 Feb 2024 • Minghan Wang, Thuy-Trang Vu, Yuxia Wang, Ehsan Shareghi, Gholamreza Haffari
Simultaneous machine translation (SimulMT) presents a challenging trade-off between translation quality and latency.
1 code implementation • 15 Feb 2024 • Yinhong Liu, Yixuan Su, Ehsan Shareghi, Nigel Collier
Recent large language models (LLMs) have shown remarkable performance in aligning generated text with user intentions across various tasks.
no code implementations • 27 Jan 2024 • Adrian Theuma, Ehsan Shareghi
Large language models (LLMs) have exhibited an array of reasoning capabilities but face challenges like error propagation and hallucination, particularly in specialised areas like finance, where data is heterogeneous, and precision is paramount.
no code implementations • 25 Jan 2024 • Jiuzhou Han, Wray Buntine, Ehsan Shareghi
We present the Uncertainty-Aware Language Agent (UALA), a framework that orchestrates the interaction between the agent and the external world using uncertainty quantification.
no code implementations • 19 Dec 2023 • Yinhong Liu, Yixuan Su, Ehsan Shareghi, Nigel Collier
Instruction-tuned large language models have shown remarkable performance in aligning generated text with user intentions across various tasks.
1 code implementation • 20 Oct 2023 • Chang Shu, Jiuzhou Han, Fangyu Liu, Ehsan Shareghi, Nigel Collier
Embodied language comprehension emphasizes that language understanding is not solely a matter of mental processing in the brain but also involves interactions with the physical and social environment.
no code implementations • 9 Oct 2023 • Baian Chen, Chang Shu, Ehsan Shareghi, Nigel Collier, Karthik Narasimhan, Shunyu Yao
Recent efforts have augmented language models (LMs) with external tools or environments, leading to the development of language agents that can reason and act.
Ranked #7 on
Question Answering
on Bamboogle
1 code implementation • 15 Sep 2023 • Jiuzhou Han, Wray Buntine, Ehsan Shareghi
Semi-structured explanation depicts the implicit process of a reasoner with an explicit representation.
no code implementations • 13 Sep 2023 • Minghan Wang, Jinming Zhao, Thuy-Trang Vu, Fatemeh Shiri, Ehsan Shareghi, Gholamreza Haffari
The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics.
1 code implementation • 28 May 2023 • Hao Yang, Jinming Zhao, Gholamreza Haffari, Ehsan Shareghi
Pre-trained speech encoders have been central to pushing state-of-the-art results across various speech understanding and generation tasks.
1 code implementation • 24 May 2023 • Yuan Yang, Siheng Xiong, Ali Payani, Ehsan Shareghi, Faramarz Fekri
Translating natural language sentences to first-order logic (NL-FOL translation) is a longstanding challenge in the NLP and formal logic literature.
1 code implementation • 21 May 2023 • Jiuzhou Han, Nigel Collier, Wray Buntine, Ehsan Shareghi
We show how a small language model could be trained to act as a verifier module for the output of an LLM~(i. e., ChatGPT, GPT-4), and to iteratively improve its performance via fine-grained corrective instructions.
1 code implementation • 6 May 2023 • Dongwon Kelvin Ryu, Meng Fang, Shirui Pan, Gholamreza Haffari, Ehsan Shareghi
Text-based games (TGs) are language-based interactive environments for reinforcement learning.
no code implementations • 26 Mar 2023 • Thuy-Trang Vu, Xuanli He, Gholamreza Haffari, Ehsan Shareghi
In very recent years more attention has been placed on probing the role of pre-training data in Large Language Models (LLMs) downstream behaviour.
no code implementations • 9 Dec 2022 • Yinhong Liu, Yixuan Su, Ehsan Shareghi, Nigel Collier
Specifically, it optimizes the joint distribution of the natural language sequence and the global content plan in a plug-and-play manner.
1 code implementation • 24 Oct 2022 • Hao Yang, Jinming Zhao, Gholamreza Haffari, Ehsan Shareghi
Pre-trained speech Transformers have facilitated great success across various speech processing tasks.
1 code implementation • 19 Oct 2022 • Jiuzhou Han, Ehsan Shareghi
Large-scale pre-trained language models (PLMs) have advanced Graph-to-Text (G2T) generation by processing the linearised version of a graph.
no code implementations • 16 Oct 2022 • Jinming Zhao, Hao Yang, Gholamreza Haffari, Ehsan Shareghi
Pre-trained speech Transformers in speech translation (ST) have facilitated state-of-the-art (SotA) results; yet, using such encoders is computationally expensive.
1 code implementation • 15 Oct 2022 • Jinming Zhao, Gholamreza Haffar, Ehsan Shareghi
Training end-to-end speech translation (ST) systems requires sufficiently large-scale data, which is unavailable for most language pairs and domains.
no code implementations • 25 Aug 2022 • Nigel H. Collier, Fangyu Liu, Ehsan Shareghi
Recent advancements in Large Language Models (LLMs) harness linguistic associations in vast natural language data for practical applications.
1 code implementation • 3 Jul 2022 • Jinming Zhao, Hao Yang, Ehsan Shareghi, Gholamreza Haffari
End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder.
2 code implementations • Findings (NAACL) 2022 • Yixuan Su, Fangyu Liu, Zaiqiao Meng, Tian Lan, Lei Shu, Ehsan Shareghi, Nigel Collier
Masked language models (MLMs) such as BERT and RoBERTa have revolutionized the field of Natural Language Understanding in the past few years.
1 code implementation • ACL 2022 • Zaiqiao Meng, Fangyu Liu, Ehsan Shareghi, Yixuan Su, Charlotte Collins, Nigel Collier
To catalyse the research in this direction, we release a well-curated biomedical knowledge probing benchmark, MedLAMA, which is constructed based on the Unified Medical Language System (UMLS) Metathesaurus.
1 code implementation • 14 Oct 2021 • Lan Zhang, Wray Buntine, Ehsan Shareghi
Deep generative models have been widely used in several areas of NLP, and various techniques have been proposed to augment them or address their training challenges.
1 code implementation • EMNLP 2021 • Jinming Zhao, Philip Arthur, Gholamreza Haffari, Trevor Cohn, Ehsan Shareghi
Most existing simultaneous machine translation (SiMT) systems are trained and evaluated on offline translation corpora.
1 code implementation • EMNLP 2021 • Zaiqiao Meng, Fangyu Liu, Thomas Hikaru Clark, Ehsan Shareghi, Nigel Collier
Infusing factual knowledge into pre-trained models is fundamental for many knowledge-intensive tasks.
1 code implementation • ACL (RepL4NLP) 2021 • Lan Zhang, Victor Prokhorov, Ehsan Shareghi
To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain.
1 code implementation • EACL 2021 • Yi Zhu, Ehsan Shareghi, Yingzhen Li, Roi Reichart, Anna Korhonen
Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP.
no code implementations • ACL 2021 • Mengjie Zhao, Yi Zhu, Ehsan Shareghi, Ivan Vulić, Roi Reichart, Anna Korhonen, Hinrich Schütze
Few-shot crosslingual transfer has been shown to outperform its zero-shot counterpart with pretrained encoders like multilingual BERT.
1 code implementation • NAACL 2021 • Fangyu Liu, Ehsan Shareghi, Zaiqiao Meng, Marco Basaldella, Nigel Collier
Despite the widespread success of self-supervised learning via masked language models (MLM), accurately capturing fine-grained semantic relationships in the biomedical domain remains a challenge.
1 code implementation • EMNLP 2020 • Marco Basaldella, Fangyu Liu, Ehsan Shareghi, Nigel Collier
Whilst there has been growing progress in Entity Linking (EL) for general language, existing datasets fail to address the complex nature of health terminology in layman's language.
1 code implementation • ACL (RepL4NLP) 2021 • Victor Prokhorov, Yingzhen Li, Ehsan Shareghi, Nigel Collier
It has been long known that sparsity is an effective inductive bias for learning efficient representation of data in vectors with fixed dimensionality, and it has been explored in many areas of representation learning.
1 code implementation • WS 2019 • Victor Prokhorov, Ehsan Shareghi, Yingzhen Li, Mohammad Taher Pilehvar, Nigel Collier
While the explicit constraint naturally avoids posterior collapse, we use it to further understand the significance of the KL term in controlling the information transmitted through the VAE channel.
no code implementations • NAACL 2019 • Ehsan Shareghi, Yingzhen Li, Yi Zhu, Roi Reichart, Anna Korhonen
While neural dependency parsers provide state-of-the-art accuracy for several languages, they still rely on large amounts of costly labeled training data.
no code implementations • NAACL 2019 • Ehsan Shareghi, Daniela Gerz, Ivan Vuli{\'c}, Anna Korhonen
In recent years neural language models (LMs) have set the state-of-the-art performance for several benchmarking datasets.
1 code implementation • TACL 2016 • Ehsan Shareghi, Matthias Petri, Gholamreza Haffari, Trevor Cohn
Efficient methods for storing and querying are critical for scaling high-order n-gram language models to large corpora.
no code implementations • 9 Mar 2015 • Ehsan Shareghi, Gholamreza Haffari, Trevor Cohn, Ann Nicholson
Linguistic structures exhibit a rich array of global phenomena, however commonly used Markov models are unable to adequately describe these phenomena due to their strong locality assumptions.