LLMs

TxnQA: Benchmarking Analytical Reasoning and Evidence Grounding over Transaction Event Sequences

CM-DPO: Constraint-Margin Direct Preference Optimization for LLM Planning

Specialists Hold, Generalists Discount: Asymmetric Equilibrium in LLM Routing Auctions

Context Contamination at USENIX Security 26 — Oral Presentation & Poster

Presented our paper "Context Contamination in LLM Analysis of Network Security Logs" at USENIX Security 2026 in Baltimore — an oral presentation plus a poster session.

Rabimba Karanjai

• Aug 12, 2026 • 1 min read

Read more

Allocation Before Ranking: Decoupled Token Compression for OmniLLMs

Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation

I-BRIDGE: Access-Adjusted Benchmarking of Synthetic AI-Assisted Immigration Decision Systems for Inclusive E-Governance

Profiler: Per-Question Persona Conditioning of Frozen LLMs via Retrieval and Fusion of Synthesized Profiles

Closing the Cost Gap in Verifier-Guided RL: A Smart Contract Case Study

Building Production AI Systems with Free Cloud GPUs

If you've been following my work on LLM-assisted code generation and AI reasoning , you know I'm always looking for ways to democratize AI development . During my recent work on …

Rabimba Karanjai

• Nov 18, 2025 • 1 min read

Read more

Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models

From General Reasoning to Domain Expertise: Uncovering the Limits of Generalization in Large Language Models

Collaboration is all you need: LLM Assisted Safe Code Translation

Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future to eDemocracy

Generating Move Smart Contracts based on Concepts

Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing

Trusted LLM Inference on the Edge with Smart Contracts

SolMover: Feasibility of Using LLMs for Translating Smart Contracts

Evaluating Irrationality in Large Language Models and Open Research Questions

All We Need is Voter Feedback: A New Paradigm to Realize Politics without Politicians Using AI Models Aligned with Voter Inputs

LookALike: Human Mimicry based collaborative decision making

Who is Smarter? An Empirical Study of AI-based Smart Contract Creation

Targeted Phishing Campaigns using Large Scale Language Models