Skip to yearly menu bar Skip to main content


Workshop

Socially Responsible Language Modelling Research (SoLaR)

Usman Anwar ⋅ David Krueger ⋅ Yejin Choi ⋅ Maarten Sap ⋅ Alan Chan ⋅ Yawen Duan ⋅ Robert Kirk ⋅ Xin Chen, Cynthia ⋅ Abulhair Saparov ⋅ Kayo Yin ⋅ Liwei Jiang ⋅ Valentina Pyatkin
Project Page [ OpenReview] 

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
9:15 AM
Opening Remark
11:00 AM
Poster session
3:20 PM
Panel
5:00 PM
Closing Remarks
The Elicitation Game: Stress-Testing Capability Elicitation Techniques
Felix Hofstätter ⋅ Jayden Teoh ⋅ Teun van der Weij ⋅ Francis Ward
Sandbag Detection through Model Impairment
Cameron Tice ⋅ Philipp Kreer ⋅ Nathan Helm-Burger ⋅ Prithviraj Singh Shahani ⋅ Fedor Ryzhenkov ⋅ Teun van der Weij ⋅ Felix Hofstätter ⋅ Jacob Haimes
Fine-Tuning Language Models for Ethical Ambiguity: A Comparative Study of Alignment with Human Responses
Pranav Senthilkumar ⋅ Visshwa Balasubramanian ⋅ Aneesa Maity ⋅ Prisha Jain ⋅ Kevin Zhu ⋅ Jonathan Lu
PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences
Daiwei Chen ⋅ Yi Chen ⋅ Aniket Rege ⋅ Ramya Korlakai Vinayak
Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
Leo McKee-Reid ⋅ Joe Needham ⋅ Maria Martinez ⋅ Christoph Sträter ⋅ Mikita Balesni
Jailbreaking Large Language Models with Symbolic Mathematics
Emet Bethany ⋅ Mazal Bethany ⋅ Juan Nolazco-Flores ⋅ Sumit Jha ⋅ peyman najafirad
LLM Hallucination Reasoning with Zero-shot Knowledge Test
Seongmin Lee ⋅ Hsiang Hsu ⋅ Richard Chen
Gender Bias in LLM-generated Interview Responses
Haein Kong ⋅ Yongsu Ahn ⋅ Sangyub Lee ⋅ Yunho Maeng
Position: AI Agents & Liability – Mapping Insights from ML and HCI Research to Policy
Connor Dunlop ⋅ Weiwei Pan ⋅ Julia Smakman ⋅ Lisa Soder ⋅ Siddharth Swaroop
SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs
Ruben Härle ⋅ Felix Friedrich ⋅ Manuel Brack ⋅ Björn Deiseroth ⋅ Patrick Schramowski ⋅ Kristian Kersting
Analyzing Probabilistic Methods for Evaluating Agent Capabilities
Axel Højmark ⋅ Govind Pimpale ⋅ Arjun Panickssery ⋅ Marius Hobbhahn ⋅ Jérémy Scheurer
CoS: Enhancing Personalization with Context Steering
Sashrika Pandey ⋅ Jerry He ⋅ Mariah Schrum ⋅ Anca Dragan
AI Sandbagging: Language Models can Selectively Underperform on Evaluations
Teun van der Weij ⋅ Felix Hofstätter ⋅ Oliver Jaffe ⋅ Samuel Brown ⋅ Francis Ward
SocialStigmaQA Spanish and Japanese - Towards Multicultural Adaptation of Social Bias Benchmarks
Clara Higuera-Cabañes ⋅ Ryo Iwaki ⋅ Beñat San Sebastian ⋅ ROSARIO UCEDA-SOSA ⋅ Manish Nagireddy ⋅ Hiroshi Kanayama ⋅ Mikio Takeuchi ⋅ Gakuto Kurata ⋅ Karthikeyan Natesan Ramamurthy
Towards Safe Multilingual Frontier AI
Arturs Kanepajs ⋅ Vladimir Ivanov ⋅ Richard Moulange
Jailbreak Defense in a Narrow Domain: Failures of Existing Methods and Improving Transcript-Based Classifiers
Tony Wang ⋅ John Hughes ⋅ Henry Sleight ⋅ Rylan Schaeffer ⋅ Rajashree Agrawal ⋅ Fazl Barez ⋅ Mrinank Sharma ⋅ Jesse Mu ⋅ Nir Shavit ⋅ Ethan Perez
Mitigating Downstream Model Risks via Model Provenance
Keyu Wang ⋅ Scott Schaffter ⋅ Abdullah Norozi Iranzad ⋅ Doina Precup ⋅ Jonathan Lebensold ⋅ Megan Risdal
Language Models Resist Alignment
Jiaming Ji ⋅ Kaile Wang ⋅ Tianyi (Alex) Qiu ⋅ Boyuan Chen ⋅ Changye Li ⋅ Hantao Lou ⋅ Jiayi Zhou ⋅ Juntao Dai ⋅ Yaodong Yang
Simulation System Towards Solving Societal-Scale Manipulation
Maximilian Puelma Touzel ⋅ Sneheel Sarangi ⋅ Austin Welch ⋅ Gayatri K ⋅ Dan Zhao ⋅ Zachary Yang ⋅ Hao Yu ⋅ Tom Gibbs ⋅ Ethan Kosak-Hine ⋅ Andreea Musulan ⋅ Camille Thibault ⋅ Reihaneh Rabbany ⋅ Jean-François Godbout ⋅ Kellin Pelrine
Shh, don't say that! Domain Certification in LLMs
Cornelius Emde ⋅ Preetham Arvind ⋅ Alasdair Paren ⋅ Maxime Kayser ⋅ Thomas Rainforth ⋅ Thomas Lukasiewicz ⋅ Philip Torr ⋅ Adel Bibi
Decreasing Inconsistencies in Differentially Private Language Models through Self-Distillation
Kieleh Ngong Ivoline Clarisse ⋅ Joseph Near ⋅ Niloofar Mireshghallah
Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
Kieleh Ngong Ivoline Clarisse ⋅ Swanand Kadhe ⋅ Hao Wang ⋅ Keerthiram Murugesan ⋅ Justin D Weisz ⋅ Amit Dhurandhar ⋅ Karthikeyan Natesan Ramamurthy
Century: A Dataset of Sensitive Historical Images
Canfer Akbulut ⋅ Kevin Robinson ⋅ Maribeth Rauh ⋅ Isabela Albuquerque ⋅ Olivia Wiles ⋅ Laura Weidinger ⋅ Verena Rieser ⋅ Yana Hasson ⋅ Nahema Marchal ⋅ Iason Gabriel ⋅ William Isaac ⋅ Lisa Anne Hendricks
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Aidan Ewart ⋅ Abhay Sheshadri ⋅ Phillip Guo ⋅ Aengus Lynch ⋅ Cindy Wu ⋅ Vivek Hebbar ⋅ Henry Sleight ⋅ Asa Cooper Stickland ⋅ Ethan Perez ⋅ Dylan Hadfield-Menell ⋅ Stephen Casper
Targeted Manipulation and Deception Emerge in LLMs Trained on User* Feedback
Marcus Williams ⋅ Micah Carroll ⋅ Constantin Weisser ⋅ Brendan Murphy ⋅ Adhyyan Narang ⋅ Anca Dragan
ReFeR: A Hierarchical Framework of Models as Evaluative and Reasoning Agents
Yaswanth Narsupalli ⋅ Abhranil Chandra ⋅ Sreevatsa Muppirala ⋅ Manish Gupta ⋅ Pawan Goyal
Measuring AI Agent Autonomy: Towards a Scalable Approach With Code Inspection
Merlin Stein ⋅ Peter Cihon ⋅ Gagan Bansal ⋅ Sam Manning
I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench
Yuan Li ⋅ Yue Huang ⋅ Yuli Lin ⋅ Siyuan Wu ⋅ Yao Wan ⋅ Lichao Sun
On Demonstration Selection for Improving Fairness in Language Models
Song Wang ⋅ Peng Wang ⋅ Yushun Dong ⋅ Tong Zhou ⋅ Lu Cheng ⋅ Yangfeng Ji ⋅ Jundong Li
HEARTS: A Holistic Framework for Explainable, Sustainable and Robust Text Stereotype Detection
Theo King ⋅ Zekun Wu ⋅ Adriano Koshiyama ⋅ Emre Kazim ⋅ Philip Treleaven
Ways Forward for Global AI Benefit Sharing
Sam Manning ⋅ Claire Dennis ⋅ Stephen Clare
Fact or Fiction? Can LLMs be Reliable Annotators for Political Truths?
Veronica Chatrath ⋅ Marcelo Lotif ⋅ Shaina Raza
An Adversarial Perspective on Machine Unlearning for AI Safety
Jakub Łucki ⋅ Boyi Wei ⋅ Yangsibo Huang ⋅ Peter Henderson ⋅ Florian Tramer ⋅ Javier Rando
The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions
Stefan Sylvius Wagner ⋅ Maike Behrendt ⋅ Marc Ziegele ⋅ Stefan Harmeling
Emergence of Steganography Between Large Language Models
Yohan Mathew ⋅ Robert McCarthy ⋅ Joan Velja ⋅ Ollie Matthews ⋅ Nandi Schoots ⋅ Dylan Cope
HarmAnalyst: Interpretable, transparent, and steerable LLM safety moderation
Jing-Jing Li ⋅ Valentina Pyatkin ⋅ Max Kleiman-Weiner ⋅ Liwei Jiang ⋅ Nouha Dziri ⋅ Anne Collins ⋅ Jana Schaich Borg ⋅ Maarten Sap ⋅ Yejin Choi ⋅ Sydney Levine
GPAI Evaluations Standards Taskforce: towards effective AI governance
Patricia Paskov ⋅ Lukas Berglund ⋅ Everett Smith ⋅ Lisa Soder
Policy Dreamer: Diverse Public Policy Generation Via Elicitation and Simulation of Human Preferences
Arjun Karanam ⋅ José Enríquez ⋅ Udari Sehwag ⋅ Michael Elabd ⋅ Kanishk Gandhi ⋅ Noah Goodman ⋅ Sanmi Koyejo
Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approach
Changgeon Ko ⋅ Jisu Shin ⋅ Hoyun Song ⋅ Jeongyeon Seo ⋅ Jong Park
On the Ethical Considerations of Generative Agents
Nyoma Diamond ⋅ Soumya Banerjee
Detection of Partially-Synthesized LLM Text
Eric Lei ⋅ Hsiang Hsu ⋅ Richard Chen
Beyond the Binary: Capturing Diverse Preferences With Reward Regularization
Vishakh Padmakumar ⋅ Chuanyang Jin ⋅ Hannah Rose Kirk ⋅ He He
Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards
Shresth Verma ⋅ Niclas Boehmer ⋅ Lingkai Kong ⋅ Milind Tambe
Monitoring Human Dependence On AI Systems With Reliance Drills
Rosco Hunter ⋅ Richard Moulange ⋅ Jamie Bernardi ⋅ Merlin Stein
CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models
Song Wang ⋅ Peng Wang ⋅ Tong Zhou ⋅ Yushun Dong ⋅ Zhen Tan ⋅ Jundong Li
Understanding Model Bias Requires Systematic Probing Across Tasks
Soline Boussard ⋅ Susannah (Cheng) Su ⋅ Helen Zhao ⋅ Siddharth Swaroop ⋅ Weiwei Pan
The Impact of Large Language Models in Academia: from Writing to Speaking
Mingmeng Geng ⋅ caixi chen ⋅ Yanru Wu ⋅ Dongping Chen ⋅ Yao Wan ⋅ Pan Zhou
THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models
Mengfei Liang ⋅ Archish Arun ⋅ Zekun Wu ⋅ CRISTIAN VILLALOBOS ⋅ Jonathan Lutch ⋅ Emre Kazim ⋅ Adriano Koshiyama ⋅ Philip Treleaven
Levels of Autonomy: Liability in the age of AI Agents
Lisa Soder ⋅ Julia Smakman ⋅ Connor Dunlop ⋅ Weiwei Pan ⋅ Siddharth Swaroop
LLM Alignment Using Soft Prompt Tuning: The Case of Cultural Alignment
Reem Masoud ⋅ Martin Ferianc ⋅ Philip Treleaven ⋅ Miguel Rodrigues
On Adversarial Robustness of Language Models in Transfer Learning
Bohdan Turbal ⋅ Anastasiia Mazur ⋅ Jiaxu Zhao ⋅ Mykola Pechenizkiy
Ablation is Not Enough to Emulate DPO: A Mechanistic Analysis of Toxicity Reduction
Yushi Yang ⋅ Filip Sondej ⋅ Harry Mayne ⋅ Adam Mahdi
Large Language Models Still Exhibit Bias in Long Text
Wonje Jeung ⋅ Dongjae Jeon ⋅ Ashkan Yousefpour ⋅ Jonghyun Choi
Auto-Enhance: Towards a Meta-Benchmark to Evaluate AI Agents' Ability to Improve Other Agents
Samuel Brown ⋅ Basil Labib ⋅ Codruta Lugoj ⋅ Sai Sasank Y
Linear Probe Penalties Reduce LLM Sycophancy
Henry Papadatos ⋅ Rachel Freedman
Report Cards: Qualitative Evaluation of LLMs Using Natural Language Summaries
Blair Yang ⋅ Fuyang Cui ⋅ Keiran Paster ⋅ Jimmy Ba ⋅ Pashootan Vaezipoor ⋅ Silviu Pitis ⋅ Michael Zhang
A Cautionary Tale on the Evaluation of Differentially Private In-Context Learning
Anjun Hu ⋅ Jiyang Guan ⋅ Philip Torr ⋅ Francesco Pinto
Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
Rylan Schaeffer ⋅ Dan Valentine ⋅ Luke Bailey ⋅ James Chua ⋅ Zane Durante ⋅ Cristobal Eyzaguirre ⋅ Joe Benton ⋅ Brando Miranda ⋅ Henry Sleight ⋅ Tony Wang ⋅ John Hughes ⋅ Rajashree Agrawal ⋅ Mrinank Sharma ⋅ Scott Emmons ⋅ Sanmi Koyejo ⋅ Ethan Perez
Developing Story: Case Studies of Generative AI’s Use in Journalism
Natalie Brigham ⋅ Chongjiu Gao ⋅ Tadayoshi Kohno ⋅ Franziska Roesner ⋅ Niloofar Mireshghallah
Developing an occupational prestige scale using Large Language Models
Robert de Vries ⋅ Mark Hill ⋅ Laura Ruis