2 citations · 4 across the 13 of their papers we have counts for
15 papers
Predicting Privileged Information Effectiveness for On-Policy Self-Distillation
Kaijian Zou, Emiliano Penaloza, MohammadHossein Rezaei +5
On-policy self-distillation (OPSD) enables large language models (LLMs) to learn from privileged information (PI) without a separate teacher model. However, prior work largely trea…
Co-Evolving Actor-Conditioned Critics for Non-Verifiable Generation
Jinyoung Kim, Muhammad Khalifa, Lajanugen Logeswaran +4
Natural-language critiques provide supervision beyond scalar rewards for non-verifiable generation, which lacks deterministic verifiers. In critique-guided refinement, a critic giv…
Understanding Knowledge Distillation in Post-Training: When It Helps and When It Fails
Xin Liu, Simin Ma, Shujian Liu +5
Large language models (LLMs) achieve strong performance across many tasks, but their high computational cost limits deployment in resource-constrained environments. Knowledge Disti…
PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration
Shuyu Zhang, Yaqi Shi, Lu Wang +2
LLM multi-agent systems often coordinate through natural-language dialogue or loosely structured shared memory, making intermediate state difficult to validate, attribute, and audi…
EvoSpec: Evolving Speculative Decoding via Real-Time Vocabulary and Parameter Adaptation
Shuyu Zhang, Lingfeng Pan, Qicheng Wang +6
Speculative decoding accelerates Large Language Model inference through draft-then-verify generation, yet lightweight draft models face coupled efficiency and quality limitations:…
Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
Muhammad Khalifa, Zohaib Khan, Omer Tafveez +2
Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence rem…
Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation
Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim +6
Large language models (LLMs) are increasingly used as judges to evaluate agent performance, particularly in non-verifiable settings where judgments rely on agent trajectories inclu…
Process Reward Models That Think
Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran +5
Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling. PRMs require step-level supervision, making them expensive to tr…
MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?
Yunxiang Zhang, Muhammad Khalifa, Shitanshu Bhushan +6
We introduce MLRC-Bench, a benchmark designed to quantify how effectively language agents can tackle challenging Machine Learning (ML) Research Competitions, with a focus on open r…
If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs
Muhammad Khalifa, Yi-Chern Tan, Arash Ahmadian +6
Model merging has shown great promise at combining expert models, but the benefit of merging is unclear when merging "generalist" models trained on many tasks. We explore merging i…
On Many-Shot In-Context Learning for Long-Context Evaluation
Kaijian Zou, Muhammad Khalifa, Lu Wang
Many-shot in-context learning (ICL) has emerged as a unique setup to both utilize and test the ability of large language models to handle long context. This paper delves into long-…
Small Language Models Need Strong Verifiers to Self-Correct Reasoning
Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran +4
Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs), where LLMs refine their solutions using self-generated criti…
Source-Aware Training Enables Knowledge Attribution in Language Models
Muhammad Khalifa, David Wadden, Emma Strubell +4
Large language models (LLMs) learn a vast amount of knowledge during pretraining, but they are often oblivious to the source(s) of such knowledge. We investigate the problem of int…
Merging Generated and Retrieved Knowledge for Open-Domain QA
Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran +3
Open-domain question answering (QA) systems are often built with retrieval modules. However, retrieving passages from a given source is known to suffer from insufficient knowledge…
LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses
Xin Liu, Muhammad Khalifa, Lu Wang
A model is considered well-calibrated when its probability estimate aligns with the actual likelihood of the output being correct. Calibrating language models (LMs) is crucial, as…