60 citations · 73 across the 15 of their papers we have counts for
18 papers
ForkPilot: Self-Evolving Policy for Retrospective Search in Long-Horizon Agents
Xinyue Zeng, Shivam Shandilya, Guilherme Potje +6
Interactive language-model agents increasingly solve complex tasks through long-horizon, multi-call reasoning, where errors in beliefs or actions can compound across tool interacti…
Self-Designed Evaluators and Warm Memory for Long-Horizon Agents
Saeid Asgari, Emre Kiciman, Leonardo de Oliveira Nunes +1
A tool-using language-model agent deployed over a long stream of tasks receives no reward, so it cannot tell whether it succeeded, cannot safely retry, and cannot label the experie…
Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising
Tianci Liu, Zihan Dong, Linjun Zhang +5
Slide design requires personalizing both deck themes and page layouts. Yet, current AI agent-based methods struggle with fine-grained, page-level design. Solely relying on prespeci…
GRIP: Feedback-Guided Prompt Retrieval for Large Multimodal Models
Garvita Allabadi, Matteo Sodano, Roberto Estevão +4
In-Context Learning (ICL) has become a powerful mechanism for adapting Large Language Models (LLMs) to new tasks without fine-tuning. Extending this concept to Large Multimodal Mod…
Diagnosing Capability Gaps in Fine-Tuning Data
Saeid Asgari Taghanaki, Rakshanda Agarwal, Bruce Sun +10
Fine-tuning large language models (LLMs) for domain-specific tasks requires training datasets that comprehensively cover the target capabilities a practitioner needs. Yet identifyi…
SibylSense: Adaptive Rubric Learning via Memory Tuning and Adversarial Probing
Yifei Xu, Guilherme Potje, Shivam Shandilya +9
Designing aligned and robust rewards for open-ended generation remains a key barrier to RL post-training. Rubrics provide structured, interpretable supervision, but scaling rubric…
Enterprise AI Must Enforce Participant-Aware Access Control
Shashank Shreedhar Bhatt, Tanmay Rajore, Khushboo Aggarwal +10
Large language models (LLMs) are increasingly deployed in enterprise settings where they interact with multiple users and are trained or fine-tuned on sensitive internal data. Whil…
Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks
Yifei Xu, Tusher Chakraborty, Srinagesh Sharma +6
Reinforcement learning (RL) training of large language models (LLMs) on unverifiable tasks is challenging even when a reasonable-quality reference answer is available. We propose a…
Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
Katie Matton, Robert Osazuwa Ness, John Guttag +1
Large language models (LLMs) are capable of generating plausible explanations of how they arrived at an answer to a question. However, these explanations can misrepresent the model…
RLTHF: Targeted Human Feedback for LLM Alignment
Yifei Xu, Tusher Chakraborty, Emre Kıcıman +11
Fine-tuning large language models (LLMs) to align with user preferences is challenging due to the high cost of quality human annotations in Reinforcement Learning from Human Feedba…
Enabling Adoption of Regenerative Agriculture through Soil Carbon Copilots
Margaret Capetz, Swati Sharma, Rafael Padilha +4
Mitigating climate change requires transforming agriculture to minimize environ mental impact and build climate resilience. Regenerative agricultural practices enhance soil organic…
Large Language Models as Co-Pilots for Causal Inference in Medical Studies
Ahmed Alaa, Rachael V. Phillips, Emre Kıcıman +3
The validity of medical studies based on real-world clinical data, such as observational studies, depends on critical assumptions necessary for drawing causal conclusions about med…
Defending Against Indirect Prompt Injection Attacks With Spotlighting
Keegan Hines, Gary Lopez, Matthew Hall +3
Large Language Models (LLMs), while powerful, are built and trained to process a single text input. In common applications, multiple inputs can be processed by concatenating them t…
Domain Adaptation for Sustainable Soil Management using Causal and Contrastive Constraint Minimization
Somya Sharma, Swati Sharma, Rafael Padilha +2
Monitoring organic matter is pivotal for maintaining soil health and can help inform sustainable soil management practices. While sensor-based soil information offers higher-fideli…
Extracting Self-Consistent Causal Insights from Users Feedback with LLMs and In-context Learning
Sara Abdali, Anjali Parikh, Steve Lim +1
Microsoft Windows Feedback Hub is designed to receive customer feedback on a wide variety of subjects including critical topics such as power and battery. Feedback is one of the mo…
Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
Jingwei Yi, Yueqi Xie, Bin Zhu +4
The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection a…
A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia
Giovanni Monea, Maxime Peyrard, Martin Josifoski +6
Large language models (LLMs) have an impressive ability to draw on novel information supplied in their context. Yet the mechanisms underlying this contextual grounding remain unkno…
TRIALSCOPE: A Unifying Causal Framework for Scaling Real-World Evidence Generation with Biomedical Language Models
Javier González, Risa Ueno, Cliff Wong +12
The rapid digitization of real-world data presents an unprecedented opportunity to optimize healthcare delivery and accelerate biomedical discovery. However, these data are often f…