Papers by Shanshan Zhao

7 papers
Training-free LLM Merging for Multi-task Learning (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing tasks.
Approach: They propose a training-free method for unifying different specialized LLMs into a single model using model-wise and layer-wise pruning and scaling.
Outcome: The proposed method outperforms existing merging techniques and surpasses models fine-tuned on combined datasets in most scenarios.
AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in multimodal large language models (MLLMs) have garnered significant attention, offering a promising pathway toward artificial general intelligence (AGI).
Approach: They propose a benchmark to evaluate associative ability while circumventing the inherent ambiguity in association tasks by decomposing ambiguities into two types and propose 'assoCiAm' they conduct extensive experiments on MLLMs, revealing a strong positive correlation between cognition and association.
Outcome: The proposed method shows that ambiguity in association evaluations makes MLLMs more random-like and the model's behavior more random.
Why and How LLMs Benefit from Knowledge Introspection in Commonsense Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) can improve commonsense reasoning by generating intermediate knowledge, but the effectiveness of this knowledge introspection is not always guaranteed.
Approach: They propose a training-free strategy that optimizes introspection via two stages: Knowledge Detection and Knowledge Regeneration.
Outcome: The proposed approach mitigates the limitations of standard introspection and has consistent performance gains across all settings.
GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks (2026.acl-long)

Copied to clipboard

Challenge: Existing toolsets that use large language models are limited to single-task settings.
Approach: They propose a framework that dynamically constructs and evolves a hierarchical graph of reusable tools across multiple scenarios.
Outcome: The proposed framework achieves up to 4.3 faster milestone completion in Minecraft compared to the previous state-of-the-art method and provides an average improvement of 9.23% over existing tool-making methods in code generation tasks and 10.03% in agent tasks.
Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding (2026.acl-long)

Copied to clipboard

Challenge: Document understanding is critical for applications from financial analysis to scientific discovery.
Approach: They propose a taxonomy based on domain, retrieval modality, and granularity and review advances involving graph structures and agentic frameworks.
Outcome: The proposed model enables holistic retrieval and reasoning across all modalities, unlocking comprehensive document intelligence.
Weight-Inherited Distillation for Task-Agnostic BERT Compression (2024.findings-naacl)

Copied to clipboard

Challenge: Knowledge Distillation (KD) is a predominant approach for BERT compression.
Approach: They propose a weight-inherited distillation method which directly transfers knowledge from the teacher to a compact student model by inheriting the weights.
Outcome: The proposed method outperforms state-of-the-art KD-based methods on GLUE and SQUAD 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