Papers by Shuang Liang

8 papers
SEGMENT+: Long Text Processing with Short-Context Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing frameworks that increase context window do not guarantee robust performance across long input tasks.
Approach: They propose a framework that enables language models to handle extended inputs within limited context windows efficiently.
Outcome: The framework improves performance on long-document question-answering and Needle-in-a-Haystack tasks.
C-World: A Computer Use Agent Environment Creator (2026.acl-long)

Copied to clipboard

Challenge: C-World enables users to build agent environments on demand.
Approach: They propose a system that enables users to build agent environments on demand.
Outcome: The proposed system outperforms baselines on 119k samples and achieves Spearman = 0.883 ranking correlation with real execution.
Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning (2026.acl-long)

Copied to clipboard

Challenge: Recent approaches to fine-tuning of large language models suffer from task interference and catastrophic forgetting.
Approach: They propose a fine-tuning framework that adapts isolation decisions based on online estimates of parameter importance.
Outcome: The proposed framework reduces interference and forgetting while releasing outdated parameters to recover plasticity.
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Incomplete learning is widespread and heterogeneous in large language models . authors identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between SFT supervision and pre-training knowledge, internal inconsistencies within SFT data, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns.
Approach: They propose a diagnostic-first framework that maps incomplete learning to causes . they identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between supervision and pre-training knowledge, internal inconsistencies, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns.
Outcome: The proposed framework maps incomplete learning to causes using observable training and inference signals.
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to generating reward models rely on voting-based mechanisms to evaluate CoT outputs.
Approach: They propose an efficient generative reward modeling framework grounded in model-internal uncertainty.
Outcome: The proposed framework reduces inference cost while improving answer accuracy.
Unilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inference (2025.emnlp-main)

Copied to clipboard

Challenge: Reasoning-focused large language models (LLMs) are rapidly evolving across various domains, yet their capabilities in handling complex legal problems remain underexplored.
Approach: They propose a large language model tailored for legal reasoning with a 7-billion parameter scale and a two-stage training strategy combining Supervised Fine-Tuning and Reinforcement Learning.
Outcome: The proposed model outperforms all models of similar scale on authoritative benchmarks and outperformed Qwen-2.5-7B-Instruct (46.6%) by an average margin of 6.6%.
Type-enriched Hierarchical Contrastive Strategy for Fine-Grained Entity Typing (2022.coling-1)

Copied to clipboard

Challenge: Experimental results show that fine-grained entity typing (FET) can be used to deduce specific semantic types of entities.
Approach: They propose a type-enriched hierarchical contrastive strategy to model type differences . their method can make type information directly perceptible and improve distinguishability .
Outcome: The proposed method can model the differences between hierarchical types and distinguish multi-grained similar types at different granularities.
Beta-LR: Interpretable Logical Reasoning based on Beta Distribution (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods to capture logical information from text are limited by the uncertainty of the text.
Approach: They propose a probabilistic embedding method to capture logical information from text . they embed texts into beta distributions on each dimension to eliminate logical uncertainty .
Outcome: The proposed method achieves competitive performances on two datasets.

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