Challenge: Existing data filtering methods rely on coarse-grained scores that lack granularity to identify nuanced semantic flaws.
Approach: They propose a "Decomposition-then-Evaluation" paradigm that breaks model responses into constituent cognitive components.
Outcome: The proposed model outperforms models trained on larger datasets in three key areas . the authors show that Logical Coherence is the most critical factor in data quality evaluation .

Similar Papers

Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning (2024.findings-acl)

Copied to clipboard

Challenge: Recent vision-language models (VLMs) have shown impressive capabilities as general visual assistants, but there are two challenges to their performance: (1) lacking task diversity in pretraining and visual instruction tuning; (2) annotation error and bias in GPT-4 synthesized instruction tuning data.
Approach: They propose a two-stage instruction tuning framework that fine tunes VLMs firstly and further tuned on GPT-4 synthesized data.
Outcome: The proposed framework outperforms the traditional single-stage visual instruction tuning framework and achieves state-of-the-art performance across a wide range of multi-modal evaluation benchmarks.
Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease.
Approach: They propose to use a multiple granularity attribute-centric benchmark and training mixture to evaluate LVLMs’ fine-grained visual comprehension ability.
Outcome: The proposed model improves on LLaVa-1.5, InstructBLIP and GPT-4V and demonstrates that they struggle to generate descriptive visual attributes based on a concept that appears within an input image despite their prominent zero-shot image captioning ability.
Call for Rigor in Reporting Quality of Instruction Tuning Data (2025.acl-short)

Copied to clipboard

Challenge: Instruction tuning is crucial for adapting large language models (LLMs) to user intentions.
Approach: They propose to use hyperparameters for training models that are often selected arbitrarily without adequate justification to make arbitrary conclusions.
Outcome: The results show that arbitrary hyperparameter decisions can make any arbitrary conclusion.
DecIF: Improving Instruction-Following through Decomposition (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to obtain high-quality instruction-following data rely heavily on existing documents and existing methods.
Approach: They propose a data synthesis framework, DecIF, which automatically generates accurate and diverse instruction-following data from scratch for supervised fine-tuning and reinforcement learning.
Outcome: Extensive experiments show that the proposed framework can synthesize accurate instruction-following data for both SFT and RL paradigms compared to baselines.
Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects (2026.findings-acl)

Copied to clipboard

Challenge: Large Vision-Language Models are hindered by a systemic efficiency barrier known as visual token dominance.
Approach: They propose a systematic taxonomy of efficiency techniques structured around the inference lifecycle . they examine visual encoding, prefilling, and decoding to understand bottlenecks .
Outcome: The proposed techniques reveal how upstream decisions dictate downstream bottlenecks . the proposed techniques include hybrid compression and modality-aware decoding .
ReportLogic: Evaluating Logical Quality in Deep Research Reports (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluation frameworks that evaluate large language models for Deep Research largely ignore this requirement.
Approach: They propose a benchmark that quantifies report-level logical quality through a reader-centric lens of auditability.
Outcome: The proposed model quantifies logical quality through a reader-centric lens of auditability.
Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning? (2025.acl-industry)

Copied to clipboard

Challenge: Large Vision-Language Models (LVLMs) are expensive and time-consuming to evaluate . however, they are limited in their use in industrial settings due to their limited availability and limited resources.
Approach: They evaluate 13 open-source LVLMs as judges for diverse chart comprehension and reasoning tasks.
Outcome: The proposed models can be used to assess chart comprehension and reasoning tasks, but they are expensive and time-consuming.
AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation (2024.acl-long)

Copied to clipboard

Challenge: Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored.
Approach: They propose a framework AbsInstruct to enhance LLMs’ abstract ability through instruction tuning.
Outcome: The proposed framework can enhance LLMs’ abstraction ability with strong generalization performance while maintaining their general instruction-following abilities.
Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning (2025.emnlp-main)

Copied to clipboard

Challenge: Visual Instruction Tuning (VIT) aims to enhance Multimodal Large Language Models (MLLMs), but its effectiveness is often compromised by corrupted datasets with issues such as hallucinated content and poor OCR quality.
Approach: They propose a corruption-robust training paradigm that surpasses existing strategies for mitigating the effects of corrupted data.
Outcome: The proposed training paradigm surpasses existing strategies for mitigating the effects of corrupted data.
An Examination of the Compositionality of Large Generative Vision-Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Recent studies have focused on the compositionality of vision-language models (VLMs) however, the performance of GVLMs in multimodal compositional reasoning remains under-explored.
Approach: They propose a syntactical bias score to quantify GVLMs' syntaktical bias . they propose 'SADE' task to assess GVLs's robustness against inclination toward syntical correctness.
Outcome: The proposed benchmarks are based on evaluation metrics and current benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations