Posters

Poster Findings of EMNLP 2026, arXiv:2605.24060

Same Ranking, Different Winner: How Scoring Targets Shape LLM Memory Benchmarks

Sugam Panthi and Rabab Abdelfattah

Open poster / New tab · 44 × 32
Poster arXiv:2608.19303

Outcome Monitors: Recovery Affordances for Silent Tool Failures

Sugam Panthi and Rabab Abdelfattah

Open poster / New tab · 44 × 32
Poster arXiv:2606.21807

Compression Is Not Evaluation-Neutral: Fixed RAG Compression Can Distort Reader Comparisons

Sugam Panthi and Rabab Abdelfattah

Open poster / New tab · 44 × 32
Poster arXiv:2610.04210

Can LLMs Separate Pasted Artifacts from User Speech? Absorption at Unmarked Prompt Seams

Sugam Panthi, Muhaiminul Yeamin, and Rabab Abdelfattah

Open poster / New tab · 44 × 32
Poster arXiv:2609.36457

Memory Consolidation Flattens the Temporal Shape of User Facts

Sugam Panthi, Muhaiminul Yeamin, Siyan Luo, and Rabab Abdelfattah

Open poster / New tab · 44 × 32
Draft Draft idea proposition, no paper yet, 2026-09-04

The Stale Answer Problem: Where the Current Statement Drops Out

Sugam Panthi

Open poster / New tab