Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication
Two recent studies (Jones et al. (2026); Zeng et al. (2026)) reach apparently contradictory conclusions about whether LVLMs can coordinate on efficient referring expressions. We control for task differences between the studies while directly comparing their prompting styles. We replicate the finding that models can coordinate efficient referring expressions when explicitly prompted to do so, suggesting that other task differences are not responsible for divergent results. However, we also find that the same models fail to infer the need for communicative efficiency from a more implicit prompt, highlighting critical differences between how humans and AI systems communicate.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Prompting Medical Large Vision-Language Models to Diagnose Pathologies by Visual Question Answering
Large Vision-Language Models (LVLMs) have achieved significant success in recent years, and they have been extended to the medical domain. Although demonstrating satisfactory performance on medical Visual Question Answer…
DiagnosticHallucinationMedical Visual Question AnsweringQuestion Answering+2Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Popular prompt strategies like Chain-of-Thought Prompting can dramatically improve the reasoning abilities of Large Language Models (LLMs) in various domains. However, such hand-crafted prompt-strategies are often sub-op…
IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning
Intent-oriented controlled video captioning aims to generate targeted descriptions for specific targets in a video based on customized user intent. Current Large Visual Language Models (LVLMs) have gained strong instruct…
Instruction FollowingVideo CaptioningDVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Models
Remote sensing (RS) large vision-language models (LVLMs) have shown strong promise across visual grounding (VG) tasks. However, existing RS VG datasets predominantly rely on explicit referring expressions-such as relativ…
Reinforcement LearningVisual GroundingImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues
Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly. Existing benchmarks use name based pr…