This paper explores techniques that focus on understanding and resolving ambiguity in language within the field of natural language processing (NLP), highlighting the complexity of linguistic phenomen…
“Fact checking can be an effective strategy against misinformation1,2,3, but its implementation at scale is impeded by the overwhelming volume of information online4. Recent artificial intelligence (A…
“Aspect-based sentiment classification is a crucial problem in fine-grained sentiment analysis, which aims to predict the sentiment polarity of the given aspect according to its context. Previous work…
“The increasing volume of online reviews has made possible the development of sentiment analysis models for determining the opinion of customers regarding different products and services. Until now, s…
we develop AUTOPROMPT, an automated method to create prompts for a diverse set of tasks, based on a gradient-guided search. Using AUTOPROMPT, we show that masked language models (MLMs) have an inheren…
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 concepts that form …
Large Language Models (LLMs) have demonstrated pronounced ideological leanings, yet the stability and depth of these positions remain poorly understood. Surface-level responses can often be manipulate…
Large Language Models (LLMs) have recently achieved impressive results in complex reasoning tasks through Chain of Thought (CoT) prompting. However, most existing CoT methods rely on using the same pr…
“Knowing something about an author’s writing style is helpful in many applications, such as predicting who the author is, determining which passages of a document the author composed, rephrasing text …
Ambiguous words are often found in modern digital communications. Lexical ambiguity challenges traditional Word Sense Disambiguation (WSD) methods, due to limited data. Consequently, the efficiency of…
We conclude that the performance of today’s LLMs can augment the CSS research pipeline in two ways: (1) serving as zero-shot data annotators on human annotation teams, and (2) bootstrapping challengin…
“However, not all YouTubers have enough time to go through all the comments on individual video. On the contrary, they must read all the comments to fully understand the public interest on their conte…
Keyphrase extraction is the task of identifying a set of keyphrases present in a document that captures its most salient topics. Scientific domain-specific pre-training has led to achieving state-of-t…
“Deciding on a product to purchase can be a time-consuming process. Every user has specific quality preferences, budget restrictions, or enjoys different item features. To distill important informatio…
“Online conversations are particularly susceptible to derailment, which can manifest itself in the form of toxic communication patterns like disrespectful comments or verbal abuse. Forecasting convers…
What if the patterns hidden within dialogue reveal more about communication than the words themselves? We introduce Conversational DNA, a novel visual language that treats any dialogue – whether betwe…
Our findings reveal that aligned models exhibit lower entropy in token predictions, form distinct clusters in the embedding space, and gravitate towards “attractor states”, indicating limited output d…
Those models take a contrastive learning approach, where they build binary classifiers to differentiate positive, or coherent examples from negative, or incoherent dialogues. Those classifiers are usu…
The recent Touché lab’s argument retrieval task focuses on controversial topics like ‘Should bottled water be banned?’ and asks to retrieve relevant pro/con arguments. Interestingly, the most effectiv…
In today’s world of fast-growing technology and an inexhaustible amount of data, there is a great need to control and verify data validity due to the possibility of fraud. Therefore, the need for a re…
“To maintain the generation quality of LLMs as well as endow models with the detoxification capability, we attempt to resolve the conflict mentioned above by decomposing the detoxification task into o…
“Affective content has been the target of a few summarization tasks such as opinion summarization [Wang and Ling, 2016]. However, opinion is only a subset of affective expressions and such task mainly…
In this study, we wish to showcase the unique utility of large language models (LLMs) in financial semantic annotation and alpha signal discovery. Leveraging a corpus of company-related tweets, we use…
“Consider these two sentences: (1) Voldemort is a bad person (2) Voldemort is not a good person. Sentence (1) and Sentence (2) convey a similar meaning, but the latter confuses hate-speech models b…
“In this study, we present a novel paradigm to evaluate fake news detectors in scenarios involving both human-written and LLM-generated misinformation. Intriguingly, our findings reveal a significant …
method leverages the inherent vulnerabilities of LLMs in handling world knowledge, which can be exploited by attackers to unconsciously spread fabricated information. Through extensive experiments, we…
In this paper, we propose a method to forecast the arrival of hostile comments on Instagram posts. In order to support different intervention strategies, as well as to assess the difficulty of variant…
“In this work, we propose making real news intriguing by learning what fake news is good at. We seek to learn what makes fake news eye-catching instead of simply mimicking the titles of fake news. Qua…
Large language models learn and continually learn through the accumulation of gradient-based updates, but how individual pieces of new information affect existing knowledge, leading to both beneficial…
“Document-level sentiment analysis aims to predict sentiment polarity of text that often takes the form of product or service reviews. Tang et al. (2015) demonstrated that modelling the individual who…
Sentiment transfer is one popular example of a text style transfer task, where the goal is to reverse the sentiment polarity of a text. With a sentiment reversal comes also a reversal in meaning. We i…
irony poses a significant challenge for Large Language Models (LLMs) due to its inherent incongruity between appearance and intent. This study examines the ability of GPT-4o to interpret irony in emoj…
While a few methods improve content, they solely transfer the style of texts to be more formal (Rao and Tetreault, 2018; Lai et al., 2021), less subjective (Pryzant et al., 2020; Liu et al., 2021a), o…
This is in sharp contrast to humans who operate at multiple levels of abstraction, well beyond single words, to analyze information and to generate creative content. In this paper, we present an attem…
we test whether GPT-3.5 and GPT-4 can derive the Big Five personality traits from users’ Facebook status updates in a zero-shot learning scenario. Our results show an average correlation of r = .29 (r…
To the human eye, AI-generated outputs of large language models have increasingly become indistinguishable from human-generated outputs. Therefore, to determine the linguistic properties that separate…
This study focused on three main research objectives: analyzing the methods used to identify deceptive online consumer reviews, evaluating insights provided by multi-method automated approaches based …
“The common underlying assumption of studies which investigate the impact of consumer reviews on product sales is that posted product ratings reflect the customers’ experience with the product, indepe…
Online discussion moderators must make adhoc decisions about whether the contributions of discussion participants are appropriate or should be removed to maintain civility. Existing research on offens…
A key focus is to use news headlines from the Wall Street Journal (WSJ) to predict the movement of stock prices on a daily timescale with OpenAI-based text embedding models used to create vector encod…
The ability of Large Language Models (LLMs) to encode syntactic and semantic structures of language is well examined in NLP. Additionally, analogy identification, in the form of word analogies are ext…
This report outlines several case studies on how actors have misused our models, as well as the steps we have taken to detect and counter such misuse. By sharing these insights, we hope to protect the…
Argumentation is the process by which humans rationally elaborate their thoughts and opinions in written (e.g., essays) or spoken (e.g., debates) contexts. Argument Mining research, however, has been …
Large language model (LLM) personalization aims to align model outputs with individuals’ unique preferences and opinions. While recent efforts have implemented various personalization methods, a unifi…
Multiple studies on content moderation have identified a problem of scale: even if antisocial behavior is a small fraction of all content that gets posted, the sheer size of modern online platforms, t…
we present Proxona, a system for defining and extracting representative audience personas from the comments. Creators converse with personas to gain insights into their preferences and engagement, sol…
“We represent a topic of discussion with a conversation graph. In such a graph, vertices represent users, and edges represent conversation activity and interactions, such as posts, comments, mentions,…
“The Internet has given word-of-mouth (WOM) a new significance by allowing individuals to express their opinions and thoughts to a global audience, and so, it is an essential aspect of e-commerce [3].…
Recent years, have seen the rise of large language models (LLMs), where practitioners use task-specific prompts; this was shown to be effective for a variety of tasks. However, when applied to semanti…
“Social media (SM) plays an increasingly important role in our lives. As of 2021, seven out of ten US adults use at least one social media platform like Facebook, Twitter, Instagram, or Pinterest [3].…
Abstract—Topic discovery in scientific literature provides valuable insights for researchers to identify emerging trends and explore new avenues for investigation, facilitating easier scientific infor…
A promising approach for knowledge-based Word Sense Disambiguation (WSD) is to select the sense whose contextualized embeddings computed for its definition sentence are closest to those computed for a…
Psychological research consistently finds that human ratings of words across diverse semantic scales can be reduced to a low-dimensional form with relatively little information loss. We find that the …
Abstract—Context recognition (SR) is a fundamental task in computer vision that aims to extract structured semantic summaries from images by identifying key events and their associated entities. Speci…
Large language models (LLMs) encapsulate vast amounts of knowledge but still remain vulnerable to external misinformation. Existing research mainly studied this susceptibility behavior in a single-tur…
One of the ways in which we might address hate speech is by contextualizing through the use of counternarratives (CN), which can not only reinforce values like tolerance but also dispel misinformation…
Consumers of services and products actively engage through social networks when they are dissatisfied, exhibiting a wide range of behaviors. Encinas and Cavazos (2021). Encinas presents a classificati…
we investigated whether linguistic features that differentiate true and false utterances in English—namely utterance length, concreteness, and particular parts-of-speech—are also present in the Polish…
We study the learnability of English filler—gap dependencies and the “island” constraints on them by assessing the generalizations made by autoregressive (incremental) language models that use deep le…
We investigate how word meanings are represented in the transformer language models. Specifically, we focus on whether transformer models employ something analogous to a lexical store - where each wor…