Kamalika Das

Researcher, Intuit

Joined

July 2022

Names

Kamalika Das (Preferred)

Emails

****@intuit.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

Researcher

Intuit (intuit.com)

2021 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Improving Tool-Using Language Agents via MDL‑Guided Rule Learning
Xiang Gao, Yuguang Yao, Qi Zhang, Kaiwen Dong, Avinash Baidya, Ruocheng Guo, Hilaf Hasson, Kamalika Das
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
REMem: Reasoning with Episodic Memory in Language Agent
Yiheng Shu, Saisri Padmaja Jonnalagedda, Xiang Gao, Bernal Jiménez Gutiérrez, Weijian Qi, Kamalika Das, Huan Sun, Yu Su
- ICLR 2026 Poster
- Readers: Everyone
ParetoMIL: Early Risk Detection in Dialogue under Weak Supervision
Avinash Baidya, Xinran Liang, Ruocheng Guo, Kamalika Das, Xiang Gao
- MTI-LLM @ NeurIPS 2025 Poster
- Readers: Everyone
PhaseEvo: Towards Unified Long-Context Prompt Optimization for Large Language Models
Wendi Cui, Jiaxin Zhang, Zhuohang Li, Hao Sun, Damien Lopez, Kamalika Das, Bradley A. Malin, Sricharan Kumar
- LCFM 2024
- Readers: Everyone
A Divide-Conquer-Reasoning Approach to Consistency Evaluation and Improvement in Blackbox Large Language Models
Wendi Cui, Jiaxin Zhang, Zhuohang Li, Damien Lopez, Kamalika Das, Bradley Malin, Sricharan Kumar
- SoLaR Poster
- Readers: Everyone
Evaluating and Improving Generation Consistency of Large Language Models via A Divide-Conquer-Reasoning Approach
Wendi Cui, Jiaxin Zhang, Zhuohang Li, Damien Lopez, Kamalika Das, Bradley Malin, Sricharan Kumar
- Submitted to ICLR 2024
- Readers: Everyone
SAC$^3$: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency
Jiaxin Zhang, Zhuohang Li, Kamalika Das, Bradley A. Malin, Sricharan Kumar
- EMNLP 2023 Findings
- Readers: Everyone

Kamalika Das

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Improving Tool-Using Language Agents via MDL‑Guided Rule Learning

REMem: Reasoning with Episodic Memory in Language Agent

ParetoMIL: Early Risk Detection in Dialogue under Weak Supervision

PhaseEvo: Towards Unified Long-Context Prompt Optimization for Large Language Models

A Divide-Conquer-Reasoning Approach to Consistency Evaluation and Improvement in Blackbox Large Language Models

Evaluating and Improving Generation Consistency of Large Language Models via A Divide-Conquer-Reasoning Approach

SAC$^3$: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency

Co-Authors