adding recent pubs

content/publication/2024-hate-geographies/cite.bib

@@ -0,0 +1,25 @@
+@inproceedings{tonneau-etal-2024-languages,
+    title = "From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets",
+    author = {Tonneau, Manuel  and
+      Liu, Diyi  and
+      Fraiberger, Samuel  and
+      Schroeder, Ralph  and
+      Hale, Scott  and
+      R{\"o}ttger, Paul},
+    editor = {Chung, Yi-Ling  and
+      Talat, Zeerak  and
+      Nozza, Debora  and
+      Plaza-del-Arco, Flor Miriam  and
+      R{\"o}ttger, Paul  and
+      Mostafazadeh Davani, Aida  and
+      Calabrese, Agostina},
+    booktitle = "Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)",
+    month = jun,
+    year = "2024",
+    address = "Mexico City, Mexico",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2024.woah-1.23",
+    doi = "10.18653/v1/2024.woah-1.23",
+    pages = "283--311",
+    abstract = "Perceptions of hate can vary greatly across cultural contexts. Hate speech (HS) datasets, however, have traditionally been developed by language. This hides potential cultural biases, as one language may be spoken in different countries home to different cultures. In this work, we evaluate cultural bias in HS datasets by leveraging two interrelated cultural proxies: language and geography. We conduct a systematic survey of HS datasets in eight languages and confirm past findings on their English-language bias, but also show that this bias has been steadily decreasing in the past few years. For three geographically-widespread languages{---}English, Arabic and Spanish{---}we then leverage geographical metadata from tweets to approximate geo-cultural contexts by pairing language and country information. We find that HS datasets for these languages exhibit a strong geo-cultural bias, largely overrepresenting a handful of countries (e.g., US and UK for English) relative to their prominence in both the broader social media population and the general population speaking these languages. Based on these findings, we formulate recommendations for the creation of future HS datasets.",
+}

content/publication/2024-hate-geographies/index.md

@@ -0,0 +1,69 @@
+---
+# Documentation: https://sourcethemes.com/academic/docs/managing-content/
+
+title: "From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets"
+authors: ["Manuel Tonneau", "Diyi Liu", "Samuel Fraiberger", "Ralph Schroeder", "Scott A. Hale", "Paul Röttger"]
+date: 2024-07-20
+doi: ""
+
+# Schedule page publish date (NOT publication's date).
+publishDate: 2023-07-12T14:48:20+01:00
+
+# Publication type.
+# Legend: 0 = Uncategorized; 1 = Conference paper; 2 = Journal article;
+# 3 = Preprint / Working Paper; 4 = Report; 5 = Book; 6 = Book section;
+# 7 = Thesis; 8 = Patent
+publication_types: ["1"]
+
+# Publication name and optional abbreviated publication name.
+publication: "WOAH at NAACL 2024"
+publication_short: "WOAH at NAACL 2024"
+
+abstract: "Perceptions of hate can vary greatly across cultural contexts. Hate speech (HS) datasets, however, have traditionally been developed by language. This hides potential cultural biases, as one language may be spoken in different countries home to different cultures. In this work, we evaluate cultural bias in HS datasets by leveraging two interrelated cultural proxies: language and geography. We conduct a systematic survey of HS datasets in eight languages and confirm past findings on their English-language bias, but also show that this bias has been steadily decreasing in the past few years. For three geographically-widespread languages -- English, Arabic and Spanish -- we then leverage geographical metadata from tweets to approximate geo-cultural contexts by pairing language and country information. We find that HS datasets for these languages exhibit a strong geo-cultural bias, largely overrepresenting a handful of countries (e.g., US and UK for English) relative to their prominence in both the broader social media population and the general population speaking these languages. Based on these findings, we formulate recommendations for the creation of future HS datasets."
+
+# Summary. An optional shortened abstract.
+summary: ""
+
+tags: ["Online Hate", "Hate Speech Detection", "NLP"]
+categories: []
+featured: false
+
+# Custom links (optional).
+#   Uncomment and edit lines below to show custom links.
+# links:
+# - name: Follow
+#   url: https://twitter.com
+#   icon_pack: fab
+#   icon: twitter
+
+url_pdf: https://aclanthology.org/2024.woah-1.23.pdf
+url_code: 
+url_dataset:
+url_poster:
+url_project:
+url_slides:
+url_source:
+url_video:
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder.
+# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight.
+image:
+  caption: 'Cultural biases in hate speech resources'
+  focal_point: "Center"
+  preview_only: false
+
+# Associated Projects (optional).
+#   Associate this publication with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `internal-project` references `content/project/internal-project/index.md`.
+#   Otherwise, set `projects: []`.
+projects: [indomita]
+
+# Slides (optional).
+#   Associate this publication with Markdown slides.
+#   Simply enter your slide deck's filename without extension.
+#   E.g. `slides: "example"` references `content/slides/example/index.md`.
+#   Otherwise, set `slides: ""`.
+slides: ""
+---

content/publication/2024-prism/cite.bib

@@ -0,0 +1,6 @@
+@inproceedings{kirk2024prism,
+  title={The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models},
+  author={Kirk, Hannah Rose and Whitefield, Alexander and R{\"o}ttger, Paul and Bean, Andrew Michael and Margatina, Katerina and Mosquera, Rafael and Ciro, Juan Manuel and Bartolo, Max and Williams, Adina and He, He and others},
+  booktitle={The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
+  year={2024}
+}

content/publication/2024-prism/index.md

@@ -0,0 +1,69 @@
+---
+# Documentation: https://sourcethemes.com/academic/docs/managing-content/
+
+title: "The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models"
+authors: ["Hannah Rose Kirk", "Alexander Whitefield", "Paul Röttger", "Andrew M. Bean", "Katerina Margatina", "Rafael Mosquera", "Juan Manuel Ciro", "Max Bartolo", "Adina Williams", "He He", "Bertie Vidgen", "Scott A. Hale"]
+date: 2024-12-03
+doi: ""
+
+# Schedule page publish date (NOT publication's date).
+publishDate: 2023-07-12T14:48:20+01:00
+
+# Publication type.
+# Legend: 0 = Uncategorized; 1 = Conference paper; 2 = Journal article;
+# 3 = Preprint / Working Paper; 4 = Report; 5 = Book; 6 = Book section;
+# 7 = Thesis; 8 = Patent
+publication_types: ["1"]
+
+# Publication name and optional abbreviated publication name.
+publication: "NeurIPS 2024"
+publication_short: "NeurIPS 2024"
+
+abstract: "Human feedback is central to the alignment of Large Language Models (LLMs). However, open questions remain about methods (how), domains (where), people (who) and objectives (to what end) of feedback processes. To navigate these questions, we introduce PRISM, a dataset that maps the sociodemographics and stated preferences of 1,500 diverse participants from 75 countries, to their contextual preferences and fine-grained feedback in 8,011 live conversations with 21 LLMs. With PRISM, we contribute (i) wider geographic and demographic participation in feedback; (ii) census-representative samples for two countries (UK, US); and (iii) individualised ratings that link to detailed participant profiles, permitting personalisation and attribution of sample artefacts. We target subjective and multicultural perspectives on value-laden and controversial issues, where we expect interpersonal and cross-cultural disagreement. We use PRISM in three case studies to demonstrate the need for careful consideration of which humans provide what alignment data."
+
+# Summary. An optional shortened abstract.
+summary: ""
+
+tags: ["Large Language Models", "AI Alignment", "NLP"]
+categories: []
+featured: false
+
+# Custom links (optional).
+#   Uncomment and edit lines below to show custom links.
+# links:
+# - name: Follow
+#   url: https://twitter.com
+#   icon_pack: fab
+#   icon: twitter
+
+url_pdf: https://arxiv.org/pdf/2404.16019
+url_code: 
+url_dataset:
+url_poster:
+url_project:
+url_slides:
+url_source:
+url_video:
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder.
+# Focal points: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight.
+image:
+  caption: 'The PRISM Dataset'
+  focal_point: "Center"
+  preview_only: false
+
+# Associated Projects (optional).
+#   Associate this publication with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `internal-project` references `content/project/internal-project/index.md`.
+#   Otherwise, set `projects: []`.
+projects: [indomita]
+
+# Slides (optional).
+#   Associate this publication with Markdown slides.
+#   Simply enter your slide deck's filename without extension.
+#   E.g. `slides: "example"` references `content/slides/example/index.md`.
+#   Otherwise, set `slides: ""`.
+slides: ""
+---