103 citations · 132 across the 9 of their papers we have counts for
12 papers
Koa-decision: Fast and Consistent Structured Decision Making with Generative LLMs
Shenghong Dai, Shiva Kumar Pentyala, Yingchi Liu +6
Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-critical applications. Existing pr…
Salesforce Koa: An Enterprise Language Model for Agentic Tool Use
Zixiang Chen, Sufeng Niu, Yingchi Liu +23
We present Salesforce Koa, an enterprise language model built by post-training the open-weight Nemotron-3-Super-120B foundation model with reinforcement learning using Group Relati…
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Zhou Yu, Bin Bi, Shiva Kumar Pentyala +8
Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harn…
Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents
Prafulla Kumar Choubey, Xiangyu Peng, Shilpa Bhagavath +3
Automated service agents require well-structured workflows to provide consistent and accurate responses to customer queries. However, these workflows are often undocumented, and th…
Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models
Aliyah R. Hsu, James Zhu, Zhichao Wang +11
LLMs have demonstrated impressive proficiency in generating coherent and high-quality text, making them valuable across a range of text-generation tasks. However, rigorous evaluati…
UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types
Zhichao Wang, Bin Bi, Can Huang +7
RL alignment methods, including RLHF and DPO, are primarily based on pairwise preference data. Although scalar or score-based feedback has been collected in some settings, it is ra…
Reinforcement Learning for LLM Post-Training: A Survey
Zhichao Wang, Kiran Ramnath, Bin Bi +9
Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding.…
PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuning
Shiva Kumar Pentyala, Zhichao Wang, Bin Bi +6
Large language models (LLMs) have shown remarkable abilities in diverse natural language processing (NLP) tasks. The LLMs generally undergo supervised fine-tuning (SFT) followed by…
Machine Learning Explanations to Prevent Overtrust in Fake News Detection
Sina Mohseni, Fan Yang, Shiva Pentyala +6
Combating fake news and misinformation propagation is a challenging task in the post-truth era. News feed and search algorithms could potentially lead to unintentional large-scale…
Towards Generalizable Deepfake Detection with Locality-aware AutoEncoder
Mengnan Du, Shiva Pentyala, Yuening Li +1
With advancements of deep learning techniques, it is now possible to generate super-realistic images and videos, i.e., deepfakes. These deepfakes could reach mass audience and resu…
XFake: Explainable Fake News Detector with Visualizations
Fan Yang, Shiva K. Pentyala, Sina Mohseni +6
In this demo paper, we present the XFake system, an explainable fake news detector that assists end-users to identify news credibility. To effectively detect and interpret the fake…
Multi-Task Networks With Universe, Group, and Task Feature Learning
Shiva Pentyala, Mengwen Liu, Markus Dreyer
We present methods for multi-task learning that take advantage of natural groupings of related tasks. Task groups may be defined along known properties of the tasks, such as task d…