Papers by Xiaosong Yuan

7 papers
TokenPenalty: Alleviating Attention Sinks and Positional Decay in LVLMs (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal large language models (MLLMs) often hallucinate due to two relevant phenomena: massive activation phenomenon and positional information decay.
Approach: They propose a token-level intervention strategy that dynamically suppresses irrelevant visual tokens while preserving key contextual signals.
Outcome: Experiments show that TokenTruth significantly improves factual consistency across MLLMs on standard image understanding benchmarks.
SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning (2025.findings-emnlp)

Copied to clipboard

Challenge: Chain-of-Thought prompting improves the math reasoning capability of large language models.
Approach: They propose a method for attribution of component-level contributions in CoT reasoning using Shapley value and a stratified sampling algorithm that significantly reduces computational complexity.
Outcome: The proposed method reduces computational complexity and provides robust correlations with model performance.
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks (2025.naacl-long)

Copied to clipboard

Challenge: Large visionlanguage models (LVLMs) are a powerful visual-language reasoning tool.
Approach: They propose to integrate attention analysis with LLaVA-CAM to determine interactions between visual representations.
Outcome: The proposed approach can be used to determine interactions between visual representations.
ART: Attention Replacement Technique to Improve Factuality in LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to mitigate hallucinations in large language models are expensive and require significant resources.
Approach: They propose a training-free method that replaces uniform attention patterns in shallow layers with local attention patterns to reduce hallucinations.
Outcome: The proposed method reduces hallucinations across multiple LLM architectures.
On the Step Length Confounding in LLM Reasoning Data Selection (2026.findings-acl)

Copied to clipboard

Challenge: Existing pipelines generate long reasoning data from more capable Large Language Models (LLMs) and apply manually heuristic or naturalness-based selection methods to filter high-quality samples.
Approach: They propose to use supervised fine-tuning to generate long reasoning data from more capable Large Language Models and apply manually heuristic or naturalness-based selection methods to filter high-quality samples.
Outcome: Experiments on four LLMs and five evaluation benchmarks show that the proposed approach is effective in mitigating step length confounding problem.
Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Multimodal large language models (MLLMs) demonstrate excellent abilities for understanding visual information, but the hallucination remains a challenging problem.
Approach: They propose a training-free approach to enhance vision attention sinks to facilitate convergence of the image token attention sink within shallow layers.
Outcome: The proposed approach improves the convergence of the image token attention sink within shallow layers and strengthens the layer’s focus on the image itself.
Reasoning Fails Where Step Flow Breaks (2026.acl-long)

Copied to clipboard

Challenge: Existing analysis tools struggle with long chain of thought traces.
Approach: They propose a saliency-inspired test-time intervention that adjusts shallow saliencies to improve accuracy on math, science, and coding tasks.
Outcome: The proposed model improves accuracy on math, science, and coding tasks without retraining.

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