7 papers
LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents
Md Nayem Uddin, Amir Saeidi, Eduardo Blanco +1
Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relev…
Dual Caption Preference Optimization for Diffusion Models
Amir Saeidi, Yiran Luo, Agneet Chatterjee +4
Recent advancements in human preference optimization, originally developed for Large Language Models (LLMs), have shown significant potential in improving text-to-image diffusion m…
When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers
Divij Handa, Zehua Zhang, Amir Saeidi +4
Recent advancements in Large Language Model (LLM) safety have primarily focused on mitigating attacks crafted in natural language or common ciphers (e.g. Base64), which are likely…
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on -bench
Venkatesh Mishra, Amir Saeidi, Satyam Raj +5
Recent advances in reasoning and planning capabilities of large language models (LLMs) have enabled their potential as autonomous agents capable of tool use in dynamic environments…
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization
Md Nayem Uddin, Amir Saeidi, Divij Handa +5
This paper introduces UnSeenTimeQA, a novel data contamination-free time-sensitive question-answering (TSQA) benchmark. It differs from existing TSQA benchmarks by avoiding web-sea…
Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization
Amir Saeidi, Shivanshu Verma, Aswin RRV +2
Reinforcement Learning with Human Feedback (RLHF) enhances the alignment of Large Language Models (LLMs). However, its limitations have led to the development of Direct Preference…