Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questions (2025.acl-long)
Copied to clipboard
| Challenge: | Existing research addresses ambiguous visual questions by rephrasing questions, but it fails to address the inherently interactive nature of user interactions with visual language models (VLMs). Existing studies focus on re-phrase questions, and lack of a benchmark to assess VLMs’ capacity for resolving ambiguities through interaction. |
| Approach: | They propose a visual question answering task that provides a natural language answer to a question based on a given image and an automated pipeline to generate ambiguity-clarification question pairs. |
| Outcome: | The proposed benchmark targets three common categories of ambiguity in visual question answering (VQA) context and encompasses various VQA scenarios. |
Similar Papers
Looking Beyond the One: Operationalizing and Eliciting Visual Ambiguity in VLLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Visual question answering systems typically collapse ambiguity, committing to a single interpretation during decoding and evaluation. |
| Approach: | They operationalize ambiguity as the existence of multiple answer-supporting regions in an image . they show that ambiguities are already encoded in their internal representations . |
| Outcome: | The proposed approach makes ambiguity observable without exhaustive annotations . ambiguities are already encoded in models, but not reliably expressed in outputs despite hidden states . |
Asking Clarification Questions to Handle Ambiguity in Open-Domain QA (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Ambiguous questions persist in open-domain question answering because formulating a precise question with a unique answer is often challenging. |
| Approach: | They propose to ask a clarification question where the user’s response will help identify the interpretation that best aligns with the user's intention. |
| Outcome: | The proposed approach achieves F1 of 61.3, 25.1, and 40.5 on the three tasks, demonstrating the need for further improvements while providing competitive baselines for future work. |
Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA (2023.acl-long)
Copied to clipboard
| Challenge: | Visual question answering models seek to answer questions about images . ambiguity can exist at all levels of linguistic analysis, but disagreements can be difficult to detect and resolve . |
| Approach: | They develop a question-generation model which integrates group information without supervision and uses a dataset of ambiguous examples to annotate answers. |
| Outcome: | The proposed model can integrate answer group information without supervision and is able to fill knowledge gaps and convey requests. |
Diversity and Consistency: Exploring Visual Question-Answer Pair Generation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing tasks to generate question-answer pairs from visual images are under-explored. |
| Approach: | They propose a task that targets question-answer pair generation from visual images. |
| Outcome: | The proposed model can generate diverse or consistent QAPs on two benchmarks. |
Selectively Answering Visual Questions (2024.findings-acl)
Copied to clipboard
| Challenge: | Large multi-modal models (LMMs) are capable of visual question answering (VQA) with unprecedented accuracy. |
| Approach: | They propose a calibration score that can be used to quantify uncertainty in visual question answering models. |
| Outcome: | The proposed calibration score is better calibrated than in text-only models for in-context learning. |
Do Video Language Models really understand the video contexts? (2025.naacl-srw)
Copied to clipboard
| Challenge: | Recent advances in VideoQA performance have shown that visual language models are effective but the processes of understanding and reasoning in VLMs remain under-explored. |
| Approach: | They propose a framework that incorporates a fine-grained question generation and answering process to measure how well VLMs understand video question answering tasks. |
| Outcome: | The proposed framework incorporates a fine-grained question generation and answering process to measure how well the responses generated by VLMs align with what the model understands. |
Model Analysis & Evaluation for Ambiguous Question Answering (2023.findings-acl)
Copied to clipboard
| Challenge: | Ambiguous questions are a challenge for Question Answering models as they require answers that cover multiple interpretations of the original query. |
| Approach: | They aim to investigate whether model/data scaling improves the answers’ quality and whether automated metrics align with human judgment. |
| Outcome: | The proposed models can generate long-form answers that combine conflicting information and provide valuable insights into the limitations of the current approaches. |
Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey (2025.emnlp-main)
Copied to clipboard
Mehrab Tanjim, Yeonjun In, Xiang Chen, Victor Bursztyn, Ryan A. Rossi, Sungchul Kim, Guang-Jie Ren, Vaishnavi Muppala, Shun Jiang, Yongsung Kim, Chanyoung Park
| Challenge: | Existing literature on ambiguity and disambiguation with Large Language Models (LLMs) ambiguities are a fundamental challenge in human-AI interactions due to complexity and flexibility of human language. |
| Approach: | They propose to define key terms and concepts and categorize various disambiguation approaches enabled by LLMs and provide a comparative analysis of their advantages and disadvantages. |
| Outcome: | The proposed frameworks are compared against different disambiguation approaches and highlight their relevance for future research. |
What’s Different between Visual Question Answering for Machine “Understanding” Versus for Accessibility? (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing benchmarking datasets for visual question answering focus on machine "understanding" but it remains unclear how progress on those datasets corresponds to improvements in this real-world use case. |
| Approach: | They evaluate the visual question answering task by evaluating a variety of VQA models. |
| Outcome: | The proposed model can achieve high scores on tasks thought to require human-like comprehension, including image tagging and captioning. |
Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | In open-domain question answering, users often ask ambiguous questions (AQs) . one approach is to identify all possible interpretations of the AQ and generate a long-form answer addressing them all. |
| Approach: | They propose a framework that generates a long-form answer addressing all possible interpretations of an ambiguous question. |
| Outcome: | The proposed framework outperforms baselines on ASQA in a few-shot setup across metrics while surpassing fully-supervised baselines trained on the whole training set in terms of Disambig-F1 and Disambigo-ROUGE. |