1 citations · 1 across the 10 of their papers we have counts for
10 papers
Dialz: A Python Toolkit for Steering Vectors
Zara Siddique, Liam D. Turner, Luis Espinosa-Anke
We introduce Dialz, a framework for advancing research on steering vectors for open-source LLMs, implemented in Python. Steering vectors allow users to modify activations at infere…
Trust in Disinformation Narratives: a Trust in the News Experiment
Hanbyul Song, Miguel F. Santos Silva, Jaume Suau +1
Understanding why people trust or distrust one another, institutions, or information is a complex task that has led scholars from various fields of study to employ diverse epistemo…
Wikipedia is Not a Dictionary, Delete! Text Classification as a Proxy for Analysing Wiki Deletion Discussions
Hsuvas Borkakoty, Luis Espinosa-Anke
Automated content moderation for collaborative knowledge hubs like Wikipedia or Wikidata is an important yet challenging task due to multiple factors. In this paper, we construct a…
Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
Zara Siddique, Irtaza Khalid, Liam D. Turner +1
We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes. We compute 8 steering vec…
Automatic Extraction of Metaphoric Analogies from Literary Texts: Task Formulation, Dataset Construction, and Evaluation
Joanne Boisson, Zara Siddique, Hsuvas Borkakoty +3
Extracting metaphors and analogies from free text requires high-level reasoning abilities such as abstraction and language understanding. Our study focuses on the extraction of the…
GEAR: A Simple GENERATE, EMBED, AVERAGE AND RANK Approach for Unsupervised Reverse Dictionary
Fatemah Almeman, Luis Espinosa-Anke
Reverse Dictionary (RD) is the task of obtaining the most relevant word or set of words given a textual description or dictionary definition. Effective RD methods have applications…
Who is better at math, Jenny or Jingzhen? Uncovering Stereotypes in Large Language Models
Zara Siddique, Liam D. Turner, Luis Espinosa-Anke
Large language models (LLMs) have been shown to propagate and amplify harmful stereotypes, particularly those that disproportionately affect marginalised communities. To understand…
Construction Artifacts in Metaphor Identification Datasets
Joanne Boisson, Luis Espinosa-Anke, Jose Camacho-Collados
Metaphor identification aims at understanding whether a given expression is used figuratively in context. However, in this paper we show how existing metaphor identification datase…
What do Deck Chairs and Sun Hats Have in Common? Uncovering Shared Properties in Large Concept Vocabularies
Amit Gajbhiye, Zied Bouraoui, Na Li +3
Concepts play a central role in many applications. This includes settings where concepts have to be modelled in the absence of sentence context. Previous work has therefore focused…
SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research
Dimosthenis Antypas, Asahi Ushio, Francesco Barbieri +5
Despite its relevance, the maturity of NLP for social media pales in comparison with general-purpose models, metrics and benchmarks. This fragmented landscape makes it hard for the…