Prompt-engineering paper accepted to ICML [R]
Summary
A paper titled 'Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity' has been accepted to ICML. It proposes a simple prompt-engineering trick for more diverse sampling, sparking debate over whether such work belongs at a top-tier ML conference.
Similar Articles
Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops
This paper diagnoses algorithmic mode collapse in code-level autonomous research loops and proposes Diversity-Aware Proposal Sampling (DAPS) as a lightweight mitigation to preserve semantic diversity and improve generalization.
ICML (DL4C) Accepted ( Few queries ) [D]
A paper on few queries has been accepted at the ICML DL4C workshop.
Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality
This paper presents a large-scale analysis of prompt lexical sensitivity in large language models, revealing a scaling law for prompt performance stability and introducing an automated Prompt-Refining Agent that reduces performance variance in tasks like code generation.
@HEI: Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning Jiayi Yuan, Hangoo Kang, …
The paper introduces MoDA, an online post-training reinforcement learning algorithm that jointly enhances quality and diversity in large language models to mitigate mode collapse, eliminating the need for hand-crafted personas or architectural modifications.
Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs
This paper introduces a validity-diversity framework attributing diversity collapse in LLMs to order and shape miscalibration during decoding, validated across 14 language models.