30 citations · 47 across the 12 of their papers we have counts for
12 papers
EviBack: Search-Agent Reinforcement Learning via Evidence-Constrained Teacher Backoff
Xiao Ma, Zhiquan Hu, Yi Wei +5
Reinforcement learning enables Agentic RAG systems to learn multi-turn search from verifiable outcome rewards, but all- zero rollout groups provide no comparative signal and may hi…
PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents
Minjia Wang, Yunfeng Wang, Xiao Ma +9
Digital footprints (records of individuals' interactions with digital systems) are essential for studying behavior, developing personalized applications, and training machine learn…
Thought Graph Traversal for Test-time Scaling in Chest X-ray VLLMs
Yue Yao, Zelin Wen, Yan Tong +5
Test-time scaling offers a promising way to improve the reasoning performance of vision-language large models (VLLMs) without additional training. In this paper, we explore a simpl…
Safety Alignment Should Be Made More Than Just a Few Tokens Deep
Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu +5
The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many…
Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses
Xiao Ma, Swaroop Mishra, Ariel Liu +6
Large language model (LLM) powered chatbots are primarily text-based today, and impose a large interactional cognitive load, especially for exploratory or sensemaking tasks such as…
Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning
Ananth Balashankar, Xiao Ma, Aradhana Sinha +4
As large language models (LLMs) are widely adopted, new safety issues and policies emerge, to which existing safety classifiers do not generalize well. If we have only observed a f…
Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting
Preethi Lahoti, Nicholas Blumm, Xiao Ma +8
A crucial challenge for generative large language models (LLMs) is diversity: when a user's prompt is under-specified, models may follow implicit assumptions while generating a res…
Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoning
Xiao Ma, Swaroop Mishra, Ahmad Beirami +2
Language models still struggle on moral reasoning, despite their impressive performance in many other tasks. In particular, the Moral Scenarios task in MMLU (Multi-task Language Un…
A Mixed-Methods Approach to Understanding User Trust after Voice Assistant Failures
Amanda Baughan, Allison Mercurio, Ariel Liu +3
Despite huge gains in performance in natural language understanding via large language models in recent years, voice assistants still often fail to meet user expectations. In this…
A Human-ML Collaboration Framework for Improving Video Content Reviews
Meghana Deodhar, Xiao Ma, Yixin Cai +3
We deal with the problem of localized in-video taxonomic human annotation in the video content moderation domain, where the goal is to identify video segments that violate granular…
R3: A Reading Comprehension Benchmark Requiring Reasoning Processes
Ran Wang, Kun Tao, Dingjie Song +4
Existing question answering systems can only predict answers without explicit reasoning processes, which hinder their explainability and make us overestimate their ability of under…
Challenges in Supporting Exploratory Search through Voice Assistants
Xiao Ma, Ariel Liu
Voice assistants have been successfully adopted for simple, routine tasks, such as asking for the weather or setting an alarm. However, as people get more familiar with voice assis…