11 citations · 47 across the 26 of their papers we have counts for
26 papers
Learning Robust Reasoning through Guided Adversarial Self-Play
Shuozhe Li, Vaishnav Tadiparthi, Kwonjoon Lee +6
Reinforcement learning from verifiable rewards (RLVR) produces strong reasoning models, yet they can fail catastrophically when the conditioning context is fallible (e.g., corrupte…
Position: Thematic Analysis of Unstructured Clinical Transcripts with Large Language Models
Seungjun Yi, Joakim Nguyen, Terence Lim +8
This position paper examines how large language models (LLMs) can support thematic analysis of unstructured clinical transcripts, a widely used but resource-intensive method for un…
SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis
Seungjun Yi, Joakim Nguyen, Huimin Xu +8
Thematic Analysis (TA) is a widely used qualitative method that provides a structured yet flexible framework for identifying and reporting patterns in clinical interview transcript…
ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
Ruiyang Zhou, Shuozhe Li, Amy Zhang +1
Self-improvement via RL often fails on complex reasoning tasks because GRPO-style post-training methods rely on the model's initial ability to generate positive samples. Without gu…
Hypothesis Testing for Quantifying LLM-Human Misalignment in Multiple Choice Settings
Harbin Hong, Sebastian Caldas, Liu Leqi
As Large Language Models (LLMs) increasingly appear in social science research (e.g., economics and marketing), it becomes crucial to assess how well these models replicate human b…
AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
Jiahao Qiu, Xinzhe Juan, Yimin Wang +11
While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the dis…
Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models
Femi Bello, Anubrata Das, Fanzhi Zeng +2
It has been hypothesized that neural networks with similar architectures trained on similar data learn shared representations relevant to the learning task. We build on this idea b…
Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection
Shrey Pandit, Ashwin Vinod, Liu Leqi +1
Aligning large language models (LLMs) to accurately detect hallucinations remains a significant challenge due to the sophisticated nature of hallucinated text. Recognizing that hal…
Learning Composable Chains-of-Thought
Fangcong Yin, Zeyu Leo Liu, Liu Leqi +2
A common approach for teaching large language models (LLMs) to reason is to train on chain-of-thought (CoT) traces of in-distribution reasoning problems, but such annotated data is…
EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations
Haotian Zhai, Connor Lawless, Ellen Vitercik +1
A fundamental problem in combinatorial optimization is identifying equivalent formulations. Despite the growing need for automated equivalence checks -- driven, for example, by opt…
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
Hui Yuan, Yifan Zeng, Yue Wu +3
Reinforcement Learning from Human Feedback (RLHF) has become the predominant approach for language model (LM) alignment. At its core, RLHF uses a margin-based loss for preference o…
Accounting for AI and Users Shaping One Another: The Role of Mathematical Models
Sarah Dean, Evan Dong, Meena Jagadeesan +1
As AI systems enter into a growing number of societal domains, these systems increasingly shape and are shaped by user preferences, opinions, and behaviors. However, the design of…
Prompting Fairness: Integrating Causality to Debias Large Language Models
Jingling Li, Zeyu Tang, Xiaoyu Liu +4
Large language models (LLMs), despite their remarkable capabilities, are susceptible to generating biased and discriminatory responses. As LLMs increasingly influence high-stakes d…
A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed Bandits
Liu Leqi, Giulio Zhou, Fatma Kılınç-Karzan +2
Personalized recommender systems suffuse modern life, shaping what media we read and what products we consume. Algorithms powering such systems tend to consist of supervised learni…
Off-Policy Risk Assessment in Markov Decision Processes
Audrey Huang, Liu Leqi, Zachary Chase Lipton +1
Addressing such diverse ends as safety alignment with human preferences, and the efficiency of learning, a growing line of reinforcement learning research focuses on risk functiona…
Supervised Learning with General Risk Functionals
Liu Leqi, Audrey Huang, Zachary C. Lipton +1
Standard uniform convergence results bound the generalization gap of the expected loss over a hypothesis class. The emergence of risk-sensitive learning requires generalization gua…
Modeling Attrition in Recommender Systems with Departing Bandits
Omer Ben-Porat, Lee Cohen, Liu Leqi +2
Traditionally, when recommender systems are formalized as multi-armed bandits, the policy of the recommender system influences the rewards accrued, but not the length of interactio…
Many Ways to Be Lonely: Fine-Grained Characterization of Loneliness and Its Potential Changes in COVID-19
Yueyi Jiang, Yunfan Jiang, Liu Leqi +1
Loneliness has been associated with negative outcomes for physical and mental health. Understanding how people express and cope with various forms of loneliness is critical for ear…
Action-Sufficient State Representation Learning for Control with Structural Constraints
Biwei Huang, Chaochao Lu, Liu Leqi +4
Perceived signals in real-world scenarios are usually high-dimensional and noisy, and finding and using their representation that contains essential and sufficient information requ…
When Curation Becomes Creation: Algorithms, Microcontent, and the Vanishing Distinction between Platforms and Creators
Liu Leqi, Dylan Hadfield-Menell, Zachary C. Lipton
Ever since social activity on the Internet began migrating from the wilds of the open web to the walled gardens erected by so-called platforms, debates have raged about the respons…
Off-Policy Risk Assessment in Contextual Bandits
Audrey Huang, Liu Leqi, Zachary C. Lipton +1
Even when unable to run experiments, practitioners can evaluate prospective policies, using previously logged data. However, while the bandits literature has adopted a diverse set…
On the Convergence and Optimality of Policy Gradient for Markov Coherent Risk
Audrey Huang, Liu Leqi, Zachary C. Lipton +1
In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes cond…
Median Optimal Treatment Regimes
Liu Leqi, Edward H. Kennedy
Optimal treatment regimes are personalized policies for making a treatment decision based on subject characteristics, with the policy chosen to maximize some value. It is common to…
Rebounding Bandits for Modeling Satiation Effects
Liu Leqi, Fatma Kilinc-Karzan, Zachary C. Lipton +1
Psychological research shows that enjoyment of many goods is subject to satiation, with short-term satisfaction declining after repeated exposures to the same item. Nevertheless, p…