16 citations · 51 across the 18 of their papers we have counts for
19 papers
Towards Diverse Scientific Hypothesis Search with Large Language Models
Haorui Wang, Parshin Shojaee, Kazem Meidani +7
Large language models (LLMs) are on the rise for accelerating scientific discovery, most recently in advanced tasks such as generating valid scientific hypotheses. Yet in many disc…
Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road
Ngoc-Hieu Nguyen, Parshin Shojaee, Phuc Minh Nguyen +4
Recent progress in large language models has led to the emergence of reasoning models, which have shown strong performance on complex tasks through specialized fine-tuning procedur…
Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context
Keivan Alizadeh, Parshin Shojaee, Minsik Cho +1
Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information…
Evaluating Large Language Models in Scientific Discovery
Zhangde Song, Jieyu Lu, Yuanqi Du +53
Large language models (LLMs) are increasingly applied to scientific research, yet prevailing science benchmarks probe decontextualized knowledge and overlook the iterative reasonin…
SURFACEBENCH: A Geometry-Aware Benchmark for Symbolic Surface Discovery
Sanchit Kabra, Shobhnik Kriplani, Parshin Shojaee +1
Equation discovery from data is a central challenge in machine learning for science, which requires the recovery of concise symbolic expressions that govern complex physical and ge…
Discovering Heuristics with Large Language Models (LLMs) for Mixed-Integer Programs: Single-Machine Scheduling
İbrahim Oğuz Çetinkaya, İ. Esra Büyüktahtakın, Parshin Shojaee +1
Our study contributes to the scheduling and combinatorial optimization literature with new heuristics discovered by leveraging the power of Large Language Models (LLMs). We focus o…
Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories
Mohammad Beigi, Ying Shen, Parshin Shojaee +5
Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster \textit{sycophancy}, i.e., the tendency of a model to agree with or re…
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
Parshin Shojaee, Iman Mirzadeh, Keivan Alizadeh +3
Recent generations of language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstra…
LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
Parshin Shojaee, Ngoc-Hieu Nguyen, Kazem Meidani +3
Scientific equation discovery is a fundamental task in the history of scientific progress, enabling the derivation of laws governing natural phenomena. Recently, Large Language Mod…
LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers
Nikhil Abhyankar, Parshin Shojaee, Chandan K. Reddy
Automated feature engineering plays a critical role in improving predictive model performance for tabular learning tasks. Traditional automated feature engineering methods are limi…
Federated Retrieval Augmented Generation for Multi-Product Question Answering
Parshin Shojaee, Sai Sree Harsha, Dan Luo +3
Recent advancements in Large Language Models and Retrieval-Augmented Generation have boosted interest in domain-specific question-answering for enterprise products. However, AI Ass…
Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges
Chandan K Reddy, Parshin Shojaee
Scientific discovery is a complex cognitive process that has driven human knowledge and technological progress for centuries. While artificial intelligence (AI) has made significan…
LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
Parshin Shojaee, Kazem Meidani, Shashank Gupta +2
Mathematical equations have been unreasonably effective in describing complex natural phenomena across various scientific disciplines. However, discovering such insightful equation…
SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training
Kazem Meidani, Parshin Shojaee, Chandan K. Reddy +1
In an era where symbolic mathematical equations are indispensable for modeling complex natural phenomena, scientific inquiry often involves collecting observations and translating…
Graph-based Multi-ODE Neural Networks for Spatio-Temporal Traffic Forecasting
Zibo Liu, Parshin Shojaee, Chandan K Reddy
There is a recent surge in the development of spatio-temporal forecasting models in the transportation domain. Long-range traffic forecasting, however, remains a challenging task d…
Transformer-based Planning for Symbolic Regression
Parshin Shojaee, Kazem Meidani, Amir Barati Farimani +1
Symbolic regression (SR) is a challenging task in machine learning that involves finding a mathematical expression for a function based on its values. Recent advancements in SR hav…
Execution-based Code Generation using Deep Reinforcement Learning
Parshin Shojaee, Aneesh Jain, Sindhu Tipirneni +1
The utilization of programming language (PL) models, pre-trained on large-scale code corpora, as a means of automating software engineering processes has demonstrated considerable…
Adaptively Weighted Top-N Recommendation for Organ Matching
Parshin Shojaee, Xiaoyu Chen, Ran Jin
Reducing the shortage of organ donations to meet the demands of patients on the waiting list has being a major challenge in organ transplantation. Because of the shortage, organ ma…
Planar Maximum Coverage Location Problem with Partial Coverage, Continuous Spatial Demand, and Adjustable Quality of Service
Manish Bansal, Parshin Shojaee
We consider a generalization of the classical planar maximum coverage location problem (PMCLP) in which partial coverage is allowed, facilities have adjustable quality of service (…