Search Results for author:
Found 73 papers, 39 papers with code
Don’t Read Too Much Into It: Adaptive Computation for Open-Domain Question Answering
Most approaches to Open-Domain Question Answering consist of a light-weight retriever that selects a set of candidate passages, and a computationally expensive reader that examines the passages to identify the correct answer.
Dot Product is All You Need: Bridging the Gap Between Item Recommendation and Link Prediction
Item recommendation (the task of predicting if a user may interact with new items from the catalogue in a recommendation system) and link prediction (the task of identifying missing links in a knowledge graph) have long been regarded as distinct problems.
Adaptive Layer Selection for Efficient Vision Transformer Fine-Tuning
To this end, in this paper we introduce an efficient fine-tuning method for ViTs called $\textbf{ALaST}$ ($\textit{Adaptive Layer Selection Fine-Tuning for Vision Transformers}$) to speed up the fine-tuning process while reducing computational cost, memory load, and training time.
Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models
The inference demand for LLMs has skyrocketed in recent months, and serving models with low latencies remains challenging due to the quadratic input length complexity of the attention layers.
SynDARin: Synthesising Datasets for Automated Reasoning in Low-Resource Languages
This shows that the generated dataset is non-trivial and can be used to evaluate reasoning capabilities in low-resource language.
Probing the Emergence of Cross-lingual Alignment during LLM Training
Multilingual Large Language Models (LLMs) achieve remarkable levels of zero-shot cross-lingual transfer performance.
A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression
The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase.
Are We Done with MMLU?
We identify and analyse errors in the popular Massive Multitask Language Understanding (MMLU) benchmark.
Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints
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.
Evaluating the Adversarial Robustness of Retrieval-Based In-Context Learning for Large Language Models
Our study reveals that retrieval-augmented models can enhance robustness against test sample attacks, outperforming vanilla ICL with a 4. 87% reduction in Attack Success Rate (ASR); however, they exhibit overconfidence in the demonstrations, leading to a 2% increase in ASR for demonstration attacks.
Transferring Troubles: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that trigger malicious outputs.
On the Independence Assumption in Neurosymbolic Learning
Many such systems assume that the probabilities of the considered symbols are conditionally independent given the input to simplify learning and reasoning.
The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models
Large Language Models (LLMs) have transformed the Natural Language Processing (NLP) landscape with their remarkable ability to understand and generate human-like text.
Forklift: An Extensible Neural Lifter
The escalating demand to migrate legacy software across different Instruction Set Architectures (ISAs) has driven the development of assembly-to-assembly translators to map between their respective assembly languages.
Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4
The NLI4CT task assesses Natural Language Inference systems in predicting whether hypotheses entail or contradict evidence from Clinical Trial Reports.
Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain
We explore the potential of Large Language Models (LLMs) to assist and potentially correct physicians in medical decision-making tasks.
Conditional computation in neural networks: principles and research trends
This article summarizes principles and ideas from the emerging area of applying \textit{conditional computation} methods to the design of neural networks.
Large language models surpass human experts in predicting neuroscience results
LLMs trained on the vast scientific literature could potentially integrate noisy yet interrelated findings to forecast novel results better than human experts.
Answerability in Retrieval-Augmented Open-Domain Question Answering
To address this limitation, we discovered an efficient approach for training models to recognize such excerpts.
FairBelief - Assessing Harmful Beliefs in Language Models
Language Models (LMs) have been shown to inherit undesired biases that might hurt minorities and underrepresented groups if such systems were integrated into real-world applications without careful fairness auditing.
Analysing The Impact of Sequence Composition on Language Model Pre-Training
In this work, we find that applying causal masking can lead to the inclusion of distracting information from previous documents during pre-training, which negatively impacts the performance of the models on language modelling and downstream tasks.
Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference
The computational cost of transformer models makes them inefficient in low-latency or low-power applications.
Using Natural Language Explanations to Improve Robustness of In-context Learning
Recent studies demonstrated that large language models (LLMs) can excel in many tasks via in-context learning (ICL).
REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization
We analyze the impact of using human highlights during training by jointly training the task model and the rationale extractor.
Temporal Smoothness Regularisers for Neural Link Predictors
Furthermore, we evaluate the impact of a wide range of temporal smoothing regularisers on two state-of-the-art temporal link prediction models.
Approximate Answering of Graph Queries
We will first provide an overview of the different query types which can be supported by these methods and datasets typically used for evaluation, as well as an insight into their limitations.
No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
The computation necessary for training Transformer-based language models has skyrocketed in recent years.
Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain
In this study, we propose a two-step PEFT framework and evaluate it in the clinical domain.
Knowledge Graph Embeddings in the Biomedical Domain: Are They Useful? A Look at Link Prediction, Rule Learning, and Downstream Polypharmacy Tasks
We achieve a three-fold improvement in terms of performance based on the HITS@10 score over previous work on the same biomedical knowledge graph.
Logical Reasoning for Natural Language Inference Using Generated Facts as Atoms
We apply our method to the highly challenging ANLI dataset, where our framework improves the performance of both a DeBERTa-base and BERT baseline.
SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations
Models that generate natural language explanations (NLEs) for their predictions have recently gained increasing interest.
Machine Learning-Assisted Recurrence Prediction for Early-Stage Non-Small-Cell Lung Cancer Patients
Conclusions: Our results show that machine learning models trained on tabular and graph data can enable objective, personalised and reproducible prediction of relapse and therefore, disease outcome in patients with early-stage NSCLC.
An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks
Experiments on various knowledge-intensive tasks such as question answering and dialogue datasets show that, simply augmenting parametric models (T5-base) using our method produces more accurate results (e. g., 25. 8 -> 44. 3 EM on NQ) while retaining a high throughput (e. g., 1000 queries/s on NQ).
Ranked #4 on
Question Answering
on KILT: ELI5
Learning Discrete Directed Acyclic Graphs via Backpropagation
Recently continuous relaxations have been proposed in order to learn Directed Acyclic Graphs (DAGs) from data by backpropagation, instead of using combinatorial optimization.
Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models
In this work, we present Adaptive IMLE (AIMLE), the first adaptive gradient estimator for complex discrete distributions: it adaptively identifies the target distribution for IMLE by trading off the density of gradient information with the degree of bias in the gradient estimates.
ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
Factorisation-based Models (FMs), such as DistMult, have enjoyed enduring success for Knowledge Graph Completion (KGC) tasks, often outperforming Graph Neural Networks (GNNs).
Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models
We can further improve model performance and span-level decisions by using the e-SNLI explanations during training.
XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking
Dialogue State Tracking (DST), a crucial component of task-oriented dialogue (ToD) systems, keeps track of all important information pertaining to dialogue history: filling slots with the most probable values throughout the conversation.
MedDistant19: Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction
Relation extraction in the biomedical domain is challenging due to the lack of labeled data and high annotation costs, needing domain experts.
Differentiable Reasoning over Long Stories -- Assessing Systematic Generalisation in Neural Models
Contemporary neural networks have achieved a series of developments and successes in many aspects; however, when exposed to data outside the training distribution, they may fail to predict correct answers.
A Probabilistic Framework for Knowledge Graph Data Augmentation
We present NNMFAug, a probabilistic framework to perform data augmentation for the task of knowledge graph completion to counter the problem of data scarcity, which can enhance the learning process of neural link predictors.
Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations
Learning good representations on multi-relational graphs is essential to knowledge base completion (KBC).
Ranked #1 on
Link Prediction
on CoDEx Small
Neuro-Symbolic Ontology-Mediated Query Answering
Recently, low-dimensional vector space representations of Knowledge Graphs (KGs) have been applied to find answers to logical queries over incomplete KGs.
Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints
Adaptive Computation (AC) has been shown to be effective in improving the efficiency of Open-Domain Question Answering (ODQA) systems.
Combining Inductive and Deductive Reasoning for Query Answering over Incomplete Knowledge Graphs
Current methods for embedding-based query answering over incomplete Knowledge Graphs (KGs) only focus on inductive reasoning, i. e., predicting answers by learning patterns from the data, and lack the complementary ability to do deductive reasoning, which requires the application of domain knowledge to infer further information.
Neural Concept Formation in Knowledge Graphs
In this work, we investigate how to learn novel concepts in Knowledge Graphs (KGs) in a principled way, and how to effectively exploit them to produce more accurate neural link prediction models.
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions
We propose Implicit Maximum Likelihood Estimation (I-MLE), a framework for end-to-end learning of models combining discrete exponential family distributions and differentiable neural components.
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them
We introduce a new QA-pair retriever, RePAQ, to complement PAQ.
Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning
In this work, we show that we can incorporate relational inductive biases, encoded in the form of relational graphs, into agents.
Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models
The first approach is an online method which is effective at removing skew at the expense of stereotype.
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
We review the EfficientQA competition from NeurIPS 2020.
Don't Read Too Much into It: Adaptive Computation for Open-Domain Question Answering
Most approaches to Open-Domain Question Answering consist of a light-weight retriever that selects a set of candidate passages, and a computationally expensive reader that examines the passages to identify the correct answer.
Complex Query Answering with Neural Link Predictors
Finally, we demonstrate that it is possible to explain the outcome of our model in terms of the intermediate solutions identified for each of the complex query atoms.
Ranked #1 on
Complex Query Answering
on NELL995
WordCraft: An Environment for Benchmarking Commonsense Agents
This is partly due to the lack of lightweight simulation environments that sufficiently reflect the semantics of the real world and provide knowledge sources grounded with respect to observations in an RL environment.
Learning Reasoning Strategies in End-to-End Differentiable Proving
Attempts to render deep learning models interpretable, data-efficient, and robust have seen some success through hybridisation with rule-based systems, for example, in Neural Theorem Provers (NTPs).
Ranked #1 on
Relational Reasoning
on CLUTRR (k=3)
Knowledge Graph Embeddings and Explainable AI
Knowledge graph embeddings are now a widely adopted approach to knowledge representation in which entities and relationships are embedded in vector spaces.
Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training
Natural Language Inference (NLI) datasets contain annotation artefacts resulting in spurious correlations between the natural language utterances and their respective entailment classes.
Undersensitivity in Neural Reading Comprehension
Current reading comprehension models generalise well to in-distribution test sets, yet perform poorly on adversarially selected inputs.
Differentiable Reasoning on Large Knowledge Bases and Natural Language
Reasoning with knowledge expressed in natural language and Knowledge Bases (KBs) is a major challenge for Artificial Intelligence, with applications in machine reading, dialogue, and question answering.
Ranked #3 on
Link Prediction
on FB122
Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations
To increase trust in artificial intelligence systems, a promising research direction consists of designing neural models capable of generating natural language explanations for their predictions.
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
In contrast, neural models can cope very well with ambiguity by learning distributed representations of words and their composition from data, but lead to models that are difficult to interpret.
Neural Variational Inference For Estimating Uncertainty in Knowledge Graph Embeddings
Recent advances in Neural Variational Inference allowed for a renaissance in latent variable models in a variety of domains involving high-dimensional data.
NLProlog: Reasoning with Weak Unification for Natural Language Question Answering
Currently, most work in natural language processing focuses on neural networks which learn distributed representations of words and their composition, thereby performing well in the presence of large linguistic variability.
Scalable Neural Theorem Proving on Knowledge Bases and Natural Language
Reasoning over text and Knowledge Bases (KBs) is a major challenge for Artificial Intelligence, with applications in machine reading, dialogue, and question answering.
Neural Variational Inference For Embedding Knowledge Graphs
While traditional variational methods derive an analytical approximation for the intractable distribution over the latent variables, here we construct an inference network conditioned on the symbolic representation of entities and relation types in the Knowledge Graph, to provide the variational distributions.
Embedding Cardinality Constraints in Neural Link Predictors
Neural link predictors learn distributed representations of entities and relations in a knowledge graph.
Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge
They are useful for understanding the shortcomings of machine learning models, interpreting their results, and for regularisation.
Towards Neural Theorem Proving at Scale
Neural models combining representation learning and reasoning in an end-to-end trainable manner are receiving increasing interest.
Jack the Reader -- A Machine Reading Framework
For example, in Question Answering, the supporting text can be newswire or Wikipedia articles; in Natural Language Inference, premises can be seen as the supporting text and hypotheses as questions.
Jack the Reader - A Machine Reading Framework
For example, in Question Answering, the supporting text can be newswire or Wikipedia articles; in Natural Language Inference, premises can be seen as the supporting text and hypotheses as questions.
Extrapolation in NLP
We argue that extrapolation to examples outside the training space will often be easier for models that capture global structures, rather than just maximise their local fit to the training data.
Adversarial Sets for Regularising Neural Link Predictors
The training objective is defined as a minimax problem, where an adversary finds the most offending adversarial examples by maximising the inconsistency loss, and the model is trained by jointly minimising a supervised loss and the inconsistency loss on the adversarial examples.
Convolutional 2D Knowledge Graph Embeddings
In this work, we introduce ConvE, a multi-layer convolutional network model for link prediction, and report state-of-the-art results for several established datasets.
Ranked #1 on
Link Prediction
on WN18
(using extra training data)
