Seraphina Goldfarb-Tarrant

33 papers A* 4Journal 19Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations. CoRR Preethi Seshadri, Samuel Cahyawijaya, Ayomide Odumakinde, Sameer Singh, Seraphina Goldfarb-Tarrant
2026	—	`conf`	MAPS: A Multilingual Benchmark for Agent Performance and Security. EACL (Findings) Omer Hofman, Jonathan Brokman, Oren Rachmil, Shamik Bose, Vikas Pahuja, Toshiya Shimizu, Trisha Starostina, Kelly Marchisio, Seraphina Goldfarb-Tarrant, Roman Vainshtein
2025	A*	`conf`	A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users. EMNLP Nishant Balepur, Matthew Shu, Yoo Yeon Sung, Seraphina Goldfarb-Tarrant, Shi Feng, Fumeng Yang, Rachel Rudinger, Jordan Lee Boyd-Graber
2025	J	`jnl`	A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users. CoRR Nishant Balepur, Matthew Shu, Yoo Yeon Sung, Seraphina Goldfarb-Tarrant, Shi Feng, Fumeng Yang, Rachel Rudinger, Jordan Lee Boyd-Graber
2025	J	`jnl`	MAPS: A Multilingual Benchmark for Global Agent Performance and Security. CoRR Omer Hofman, Oren Rachmil, Shamik Bose, Vikas Pahuja, Jonathan Brokman, Toshiya Shimizu, Trisha Starostina, Kelly Marchisio, Seraphina Goldfarb-Tarrant, Roman Vainshtein
2025	—	`conf`	Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts. ACL (1) Hongyu Chen, Seraphina Goldfarb-Tarrant
2025	J	`jnl`	Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts. CoRR Hongyu Chen, Seraphina Goldfarb-Tarrant
2025	J	`jnl`	Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them. CoRR Neel Rajani, Aryo Pradipta Gema, Seraphina Goldfarb-Tarrant, Ivan Titov
2025	—	`conf`	Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contexts. IJCNLP-AACL (long papers) Preethi Seshadri, Hongyu Chen, Sameer Singh, Seraphina Goldfarb-Tarrant
2025	J	`jnl`	The Multilingual Divide and Its Impact on Global AI Safety. CoRR Aidan Peppin, Julia Kreutzer, Alice Schoenauer Sebag, Kelly Marchisio, Beyza Ermis, John Dang, Samuel Cahyawijaya, Shivalika Singh, Seraphina Goldfarb-Tarrant, Viraat Aryabumi, Aakanksha, Wei-Yin Ko, Ahmet Üstün, Matthias Gallé, Marzieh Fadaee, Sara Hooker
2025	J	`jnl`	Who Does the Giant Number Pile Like Best: Analyzing Fairness in Hiring Contexts. CoRR Preethi Seshadri, Seraphina Goldfarb-Tarrant
2024	A*	`conf`	A SMART Mnemonic Sounds like "Glue Tonic": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick. EMNLP Nishant Balepur, Matthew Shu, Alexander Miserlis Hoyle, Alison Robey, Shi Feng, Seraphina Goldfarb-Tarrant, Jordan L. Boyd-Graber
2024	J	`jnl`	A SMART Mnemonic Sounds like "Glue Tonic": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick. CoRR Nishant Balepur, Matthew Shu, Alexander Miserlis Hoyle, Alison Robey, Shi Feng, Seraphina Goldfarb-Tarrant, Jordan L. Boyd-Graber
2024	J	`jnl`	Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning. CoRR Aakanksha, Arash Ahmadian, Seraphina Goldfarb-Tarrant, Beyza Ermis, Marzieh Fadaee, Sara Hooker
2024	J	`jnl`	MultiContrievers: Analysis of Dense Retrieval Representations. CoRR Seraphina Goldfarb-Tarrant, Pedro Rodriguez, Jane Dwivedi-Yu, Patrick S. H. Lewis
2024	A*	`conf`	The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm. EMNLP Aakanksha, Arash Ahmadian, Beyza Ermis, Seraphina Goldfarb-Tarrant, Julia Kreutzer, Marzieh Fadaee, Sara Hooker
2024	J	`jnl`	The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm. CoRR Aakanksha, Arash Ahmadian, Beyza Ermis, Seraphina Goldfarb-Tarrant, Julia Kreutzer, Marzieh Fadaee, Sara Hooker
2023	—	`conf`	Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages. ACL (Findings) Seraphina Goldfarb-Tarrant, Adam Lopez, Roi Blanco, Diego Marcheggiani
2023	J	`jnl`	Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages. CoRR Seraphina Goldfarb-Tarrant, Adam Lopez, Roi Blanco, Diego Marcheggiani
2023	A*	`conf`	Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis. EMNLP Seraphina Goldfarb-Tarrant, Björn Ross, Adam Lopez
2023	J	`jnl`	Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis. CoRR Seraphina Goldfarb-Tarrant, Björn Ross, Adam Lopez
2023	J	`jnl`	This Prompt is Measuring : Evaluating Bias Evaluation in Language Models. CoRR Seraphina Goldfarb-Tarrant, Eddie Ungless, Esma Balkir, Su Lin Blodgett
2023	—	`conf`	This prompt is measuring \textlessmask\textgreater: evaluating bias evaluation in language models. ACL (Findings) Seraphina Goldfarb-Tarrant, Eddie Ungless, Esma Balkir, Su Lin Blodgett
2022	—	`conf`	How Gender Debiasing Affects Internal Model Representations, and Why It Matters. NAACL-HLT Hadas Orgad, Seraphina Goldfarb-Tarrant, Yonatan Belinkov
2022	J	`jnl`	How Gender Debiasing Affects Internal Model Representations, and Why It Matters. CoRR Hadas Orgad, Seraphina Goldfarb-Tarrant, Yonatan Belinkov
2021	—	`conf`	Intrinsic Bias Metrics Do Not Correlate with Application Bias. ACL/IJCNLP (1) Seraphina Goldfarb-Tarrant, Rebecca Marchant, Ricardo Muñoz Sánchez, Mugdha Pandya, Adam Lopez
2020	—	`conf`	Content Planning for Neural Story Generation with Aristotelian Rescoring. EMNLP (1) Seraphina Goldfarb-Tarrant, Tuhin Chakrabarty, Ralph M. Weischedel, Nanyun Peng
2020	J	`jnl`	Content Planning for Neural Story Generation with Aristotelian Rescoring. CoRR Seraphina Goldfarb-Tarrant, Tuhin Chakrabarty, Ralph M. Weischedel, Nanyun Peng
2020	J	`jnl`	Intrinsic Bias Metrics Do Not Correlate with Application Bias. CoRR Seraphina Goldfarb-Tarrant, Rebecca Marchant, Ricardo Muñoz Sánchez, Mugdha Pandya, Adam Lopez
2020	—	`conf`	Scaling Systematic Literature Reviews with Machine Learning Pipelines. SDP@EMNLP Seraphina Goldfarb-Tarrant, Alexander Robertson, Jasmina Lazic, Theodora Tsouloufi, Louise Donnison, Karen Smyth
2020	J	`jnl`	Scaling Systematic Literature Reviews with Machine Learning Pipelines. CoRR Seraphina Goldfarb-Tarrant, Alexander Robertson, Jasmina Lazic, Theodora Tsouloufi, Louise Donnison, Karen Smyth
2019	—	`conf`	Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation. NAACL-HLT (Demonstrations) Seraphina Goldfarb-Tarrant, Haining Feng, Nanyun Peng
2019	J	`jnl`	Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation. CoRR Seraphina Goldfarb-Tarrant, Haining Feng, Nanyun Peng