Recent searches

No recent searches

Search options

Only available when logged in.
sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!

Administered by:

Server stats:

597
active users

sigmoid.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.2

#toread

4 posts4 participants0 posts today
Katherine Pickett, Editor

Thrilled to have this wonderful writeup about Debra Lee Won't Break in the July TBR Books section of Washington City Paper.

"Pickett’s novel promises the kind of emotional depth and grit I crave."

Read the full review:

washingtoncitypaper.com/articl

#books #NewBook #Fiction #ToRead @bookstodon #bookstodon

Washington City Paper · Spot LIT: Zach Powers Takes Over at the Writer’s CenterBy Hannah Grieco
Fabio Giglietto

#toread #paper Evaluating how LLM annotations represent diverse views on contentious topics by Megan A. Brown et al. arxiv.org/abs/2503.23243v2

arXiv logo
arXiv.orgEvaluating how LLM annotations represent diverse views on contentious topicsResearchers have proposed the use of generative large language models (LLMs) to label data for research and applied settings. This literature emphasizes the improved performance of these models relative to other natural language models, noting that generative LLMs typically outperform other models and even humans across several metrics. Previous literature has examined bias across many applications and contexts, but less work has focused specifically on bias in generative LLMs' responses to subjective annotation tasks. This bias could result in labels applied by LLMs that disproportionately align with majority groups over a more diverse set of viewpoints. In this paper, we evaluate how LLMs represent diverse viewpoints on these contentious tasks. Across four annotation tasks on four datasets, we show that LLMs do not show systematic substantial disagreement with annotators on the basis of demographics. Rather, we find that multiple LLMs tend to be biased in the same directions on the same demographic categories within the same datasets. Moreover, the disagreement between human annotators on the labeling task -- a measure of item difficulty -- is far more predictive of LLM agreement with human annotators. We conclude with a discussion of the implications for researchers and practitioners using LLMs for automated data annotation tasks. Specifically, we emphasize that fairness evaluations must be contextual, model choice alone will not solve potential issues of bias, and item difficulty must be integrated into bias assessments.
Fabio Giglietto

#toread #paper They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discourse by Walter Paci, Alessandro Panunzi, Sandro Pezzelle arxiv.org/abs/2506.06775v1

arXiv.orgThey want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political DiscourseImplicit content plays a crucial role in political discourse, where speakers systematically employ pragmatic strategies such as implicatures and presuppositions to influence their audiences. Large Language Models (LLMs) have demonstrated strong performance in tasks requiring complex semantic and pragmatic understanding, highlighting their potential for detecting and explaining the meaning of implicit content. However, their ability to do this within political discourse remains largely underexplored. Leveraging, for the first time, the large IMPAQTS corpus, which comprises Italian political speeches with the annotation of manipulative implicit content, we propose methods to test the effectiveness of LLMs in this challenging problem. Through a multiple-choice task and an open-ended generation task, we demonstrate that all tested models struggle to interpret presuppositions and implicatures. We conclude that current LLMs lack the key pragmatic capabilities necessary for accurately interpreting highly implicit language, such as that found in political discourse. At the same time, we highlight promising trends and future directions for enhancing model performance. We release our data and code at https://github.com/WalterPaci/IMPAQTS-PID
Fabio Giglietto

#toread Coordinated Inauthentic Behavior on TikTok: Challenges and Opportunities for Detection in a Video-First Ecosystem arxiv.org/abs/2505.10867

arXiv.orgCoordinated Inauthentic Behavior on TikTok: Challenges and Opportunities for Detection in a Video-First EcosystemDetecting coordinated inauthentic behavior (CIB) is central to the study of online influence operations. However, most methods focus on text-centric platforms, leaving video-first ecosystems like TikTok largely unexplored. To address this gap, we develop and evaluate a computational framework for detecting CIB on TikTok, leveraging a network-based approach adapted to the platform's unique content and interaction structures. Building on existing approaches, we construct user similarity networks based on shared behaviors, including synchronized posting, repeated use of similar captions, multimedia content reuse, and hashtag sequence overlap, and apply graph pruning techniques to identify dense networks of likely coordinated accounts. Analyzing a dataset of 793K TikTok videos related to the 2024 U.S. Presidential Election, we uncover a range of coordinated activities, from synchronized amplification of political narratives to semi-automated content replication using AI-generated voiceovers and split-screen video formats. Our findings show that while traditional coordination indicators generalize well to TikTok, other signals, such as those based on textual similarity of video transcripts or Duet and Stitch interactions, prove ineffective, highlighting the platform's distinct content norms and interaction mechanics. This work provides the first empirical foundation for studying and detecting CIB on TikTok, paving the way for future research into influence operations in short-form video platforms.
TrendingLive feeds
About