When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
Paper • 2606.32029 • Published • 3
Dipankar Sarkar PRO
dipankarsarkar
·
AI & ML interests
Building the AI-native stack. Agents as infrastructure, safety as architecture, performance as plumbing. I publish the receipts: papers, datasets, demos.
Recent Activity
upvoted a paper 16 minutes ago
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors upvoted a paper 16 minutes ago
Autonomous Scientific Discovery via Iterative Meta-Reflection upvoted a paper 17 minutes ago
ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE ServingOrganizations
upvoted 2
papers 16 minutes ago
upvoted 2
papers 17 minutes ago
upvoted a paper about 15 hours ago
upvoted a paper about 16 hours ago
upvoted 3
papers about 17 hours ago
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
Paper • 2605.31264 • Published • 123
AI-Trader: Benchmarking Autonomous Agents in Real-Time Financial Markets
Paper • 2512.10971 • Published • 12
MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
Paper • 2606.30406 • Published • 6
upvoted a paper about 18 hours ago
upvoted 7
papers about 19 hours ago
Who judges the judges? Governance from metrics: a runtime framework for continuous LLM compliance monitoring
Paper • 2605.24737 • Published • 2
Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents
Paper • 2601.15322 • Published • 1
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories
Paper • 2604.07223 • Published • 1
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
Paper • 2604.10577 • Published • 27
Multi-Block Diffusion Language Models
Paper • 2606.29215 • Published • 24
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
Paper • 2606.29082 • Published • 26
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
Paper • 2606.32034 • Published • 9
upvoted 3
papers about 21 hours ago
DataEvolver: Self-Evolving Multi-Agent Data Construction for Text-Rich Image Generation
Paper • 2606.31537 • Published • 17
Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction
Paper • 2606.28186 • Published • 6
Xiaomi-GUI-0 Technical Report
Paper • 2606.31410 • Published • 10