67 citations · 217 across the 55 of their papers we have counts for
59 papers
Efficient Seq2seq Coreference Resolution Using Entity Representations
Matt Grenander, Shay B. Cohen, Mark Steedman
Seq2seq coreference models have introduced a new paradigm for coreference resolution by learning to generate text corresponding to coreference labels, without requiring task-specif…
Spectral Editing of Activations for Large Language Model Alignment
Yifu Qiu, Zheng Zhao, Yftah Ziser +3
Large language models (LLMs) often exhibit undesirable behaviours, such as generating untruthful or biased content. Editing their internal representations has been shown to be effe…
`Keep it Together': Enforcing Cohesion in Extractive Summaries by Simulating Human Memory
Ronald Cardenas, Matthias Galle, Shay B. Cohen
Extractive summaries are usually presented as lists of sentences with no expected cohesion between them. In this paper, we aim to enforce cohesion whilst controlling for informativ…
AMR Parsing is Far from Solved: GrAPES, the Granular AMR Parsing Evaluation Suite
Jonas Groschwitz, Shay B. Cohen, Lucia Donatelli +1
We present the Granular AMR Parsing Evaluation Suite (GrAPES), a challenge set for Abstract Meaning Representation (AMR) parsing with accompanying evaluation metrics. AMR parsers n…
Are Large Language Models Temporally Grounded?
Yifu Qiu, Zheng Zhao, Yftah Ziser +3
Are Large language models (LLMs) temporally grounded? Since LLMs cannot perceive and interact with the environment, it is impossible to answer this question directly. Instead, we p…
Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation
Yifu Qiu, Varun Embar, Shay B. Cohen +1
Knowledge-to-text generators often struggle to faithfully generate descriptions for the input facts: they may produce hallucinations that contradict the input, or describe facts no…
Can Large Language Models Follow Concept Annotation Guidelines? A Case Study on Scientific and Financial Domains
Marcio Fonseca, Shay B. Cohen
Although large language models (LLMs) exhibit remarkable capacity to leverage in-context demonstrations, it is still unclear to what extent they can learn new concepts or facts fro…
A Joint Matrix Factorization Analysis of Multilingual Representations
Zheng Zhao, Yftah Ziser, Bonnie Webber +1
We present an analysis tool based on joint matrix factorization for comparing latent representations of multilingual and monolingual models. An alternative to probing, this tool al…
Neuron to Graph: Interpreting Language Model Neurons at Scale
Alex Foote, Neel Nanda, Esben Kran +3
Advances in Large Language Models (LLMs) have led to remarkable capabilities, yet their inner mechanisms remain largely unknown. To understand these models, we need to unravel the…
Knowledge Base Question Answering for Space Debris Queries
Paul Darm, Antonio Valerio Miceli-Barone, Shay B. Cohen +1
Space agencies execute complex satellite operations that need to be supported by the technical knowledge contained in their extensive information systems. Knowledge bases (KB) are…
Sentence-Incremental Neural Coreference Resolution
Matt Grenander, Shay B. Cohen, Mark Steedman
We propose a sentence-incremental neural coreference resolution system which incrementally builds clusters after marking mention boundaries in a shift-reduce method. The system is…
The Larger They Are, the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python
Antonio Valerio Miceli-Barone, Fazl Barez, Ioannis Konstas +1
Large Language Models (LLMs) have successfully been applied to code generation tasks, raising the question of how well these models understand programming. Typical programming lang…
Detecting and Mitigating Hallucinations in Multilingual Summarisation
Yifu Qiu, Yftah Ziser, Anna Korhonen +2
Hallucinations pose a significant challenge to the reliability of neural models for abstractive summarisation. While automatically generated summaries may be fluent, they often lac…
PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India
Ashok Urlana, Pinzhen Chen, Zheng Zhao +3
This paper introduces PMIndiaSum, a multilingual and massively parallel summarization corpus focused on languages in India. Our corpus provides a training and testing ground for fo…
BERT is not The Count: Learning to Match Mathematical Statements with Proofs
Weixian Waylon Li, Yftah Ziser, Maximin Coavoux +1
We introduce a task consisting in matching a proof to a given mathematical statement. The task fits well within current research on Mathematical Information Retrieval and, more gen…
Causal Explanations for Sequential Decision-Making in Multi-Agent Systems
Balint Gyevnar, Cheng Wang, Christopher G. Lucas +2
We present CEMA: Causal Explanations in Multi-Agent systems; a framework for creating causal natural language explanations of an agent's decisions in dynamic sequential multi-agent…
Erasure of Unaligned Attributes from Neural Representations
Shun Shao, Yftah Ziser, Shay Cohen
We present the Assignment-Maximization Spectral Attribute removaL (AMSAL) algorithm, which erases information from neural representations when the information to be erased is impli…
Abstractive Summarization Guided by Latent Hierarchical Document Structure
Yifu Qiu, Shay B. Cohen
Sequential abstractive neural summarizers often do not use the underlying structure in the input article or dependencies between the input sentences. This structure is essential to…
Understanding Domain Learning in Language Models Through Subpopulation Analysis
Zheng Zhao, Yftah Ziser, Shay B. Cohen
We investigate how different domains are encoded in modern neural network architectures. We analyze the relationship between natural language domains, model size, and the amount of…
A Human-Centric Method for Generating Causal Explanations in Natural Language for Autonomous Vehicle Motion Planning
Balint Gyevnar, Massimiliano Tamborski, Cheng Wang +3
Inscrutable AI systems are difficult to trust, especially if they operate in safety-critical settings like autonomous driving. Therefore, there is a need to build transparent and q…
Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents
Marcio Fonseca, Yftah Ziser, Shay B. Cohen
We argue that disentangling content selection from the budget used to cover salient content improves the performance and applicability of abstractive summarizers. Our method, Facto…
Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information
Shun Shao, Yftah Ziser, Shay B. Cohen
We describe a simple and effective method (Spectral Attribute removaL; SAL) to remove private or guarded information from neural representations. Our method uses matrix decompositi…
Co-training an Unsupervised Constituency Parser with Weak Supervision
Nickil Maveli, Shay B. Cohen
We introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence. There are two types of classi…
Unsupervised Extractive Summarization by Human Memory Simulation
Ronald Cardenas, Matthias Galle, Shay B. Cohen
Summarization systems face the core challenge of identifying and selecting important information. In this paper, we tackle the problem of content selection in unsupervised extracti…