1 citations · 1 across the 4 of their papers we have counts for
8 papers
Alignment by Confident Debate: Preference Learning from Multi-Agent Debate
Nikhil Verma, Dingxian Wang, Mohammad Reza Rezaei +2
Post-training language models for reasoning typically rely on gold answers, task-specific verifiers, or learned reward models, limiting scalability when such signals are scarce. Mu…
PAYWORTHY: Can LLMs Predict Which Freelance Jobs an AI Agent Will Complete?
Mohammad Reza Rezaei, Dingxian Wang, Brett Levert +3
Before an AI agent takes on a paid job, someone has to judge whether it is likely to succeed. We test whether frontier language models can make this call before any attempt. We pro…
Online Label-Free Gradient Matching for Continual Language Model Training
Sajjad Pakdamansavoji, Mohammad Reza Rezaei, Ilija Subasic +3
Language models in customer-facing products must be continually updated, since the data they serve shifts over time. As retraining on the full accumulated data is impractical, each…
Fragility Is Not Reducible to Hardness: Conditional Causal Difficulty for LLMs
Mohammad Reza Rezaei, Dingxian Wang, Nikhil Verma +3
Large language models show large and seemingly arbitrary performance drops when a task is rewritten in ways that leave its requirements untouched. We recast task difficulty as a ca…
Alternators With Noise Models
Mohammad R. Rezaei, Adji Bousso Dieng
Alternators have recently been introduced as a framework for modeling time-dependent data. They often outperform other popular frameworks, such as state-space models and diffusion…
Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs
Mohammad Reza Rezaei, Adji Bousso Dieng
Retrieval-augmented generation (RAG) enhances large language models (LLMs) for domain-specific question-answering (QA) tasks by leveraging external knowledge sources. However, trad…
The Alpha-Alternator: Dynamic Adaptation To Varying Noise Levels In Sequences Using The Vendi Score For Improved Robustness and Performance
Mohammad Reza Rezaei, Adji Bousso Dieng
Current state-of-the-art dynamical models, such as Mamba, assume the same level of noisiness for all elements of a given sequence, which limits their performance on noisy temporal…
AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoning
Mohammad Reza Rezaei, Maziar Hafezi, Amit Satpathy +2
Recent advancements in QA with LLM, like GPT-4, have shown limitations in handling complex multi-hop queries. We propose AT-RAG, a novel multistep RAG incorporating topic modeling…