9 papers
PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language
Hongliang Lu, Zhong Li, Yuxuan Chen +3
Optimization modeling is the process of translating real-world decision problems, often described in natural language, into formal mathematical formulations and executable solver c…
Constructing Industrial-Scale Optimization Modeling Benchmark
Zhong Li, Hongliang Lu, Tao Wei +5
Optimization modeling underpins decision-making in logistics, manufacturing, energy, and finance, yet translating natural-language requirements into correct optimization formulatio…
MARVEL: A Multi Agent-based Research Validator and Enabler using Large Language Models
Nikhil Mukund, Yifang Luo, Fan Zhang +2
We present MARVEL (https://ligogpt.mit.edu/marvel), a locally deployable, open-source framework for domain-aware question answering and assisted scientific research. It is designed…
Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap
Feiyang Huang, Yuqiang Sun, Fan Zhang +3
Large Language Models (LLMs) have shown promising performance in software vulnerability detection, particularly after domain-specific Supervised Fine-Tuning (SFT). However, it rema…
EssayCBM: Rubric-Aligned Concept Bottleneck Models for Transparent Essay Grading
Kumar Satvik Chaudhary, Chengshuai Zhao, Fan Zhang +3
Automated essay scoring (AES) has advanced significantly with neural language models, yet most systems remain opaque, offering little visibility into how grades are produced. In ed…
MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
Chenlu Ding, Jiancan Wu, Leheng Sheng +4
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities across vision-language tasks, yet their large-scale deployment raises pressing concerns about mem…
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Kun Wang, Guibin Zhang, Zhenhong Zhou +100
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communi…
Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation
Wenlong Meng, Fan Zhang, Wendao Yao +4
Large language models (LLMs) have demonstrated significant utility in a wide range of applications; however, their deployment is plagued by security vulnerabilities, notably jailbr…
Minimal Evidence Group Identification for Claim Verification
Xiangci Li, Sihao Chen, Rajvi Kapadia +2
Claim verification in real-world settings (e.g. against a large collection of candidate evidences retrieved from the web) typically requires identifying and aggregating a complete…