Papers by Tianyang Xu

17 papers
Towards Enhanced Immersion and Agency for LLM-based Interactive Drama (2025.acl-long)

Copied to clipboard

Challenge: Existing studies have focused on the role of immersion and agency in interactive drama.
Approach: They propose a playwriting-guided generation method that helps LLMs craft dramatic stories with substantially improved structures and narrative quality.
Outcome: The proposed method improves storytelling quality and immersion and agency, while allowing agents to refine their reactions to align with the player’s intentions.
Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing models for task-specific natural language generation do not contain any labeled examples.
Approach: They propose a variational autoencoder with disentanglement priors for task-specific natural language generation with none or a handful of task-related labeled examples.
Outcome: The proposed model outperforms baseline models in terms of data augmentation and text style transfer in the few-shot setting.
Sensitivity-LoRA : Low-Load Sensitivity-Based Fine-Tuning for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Low-Rank Adaptation (LoRA) is a promising approach to adapting LLMs to specialized tasks . existing rank allocation techniques remain computationally inefficient and unstable .
Approach: They propose a low-rank adapted model that approximates model weight updates using low-ranked decomposition.
Outcome: The proposed method is limited by its uniform rank allocation to each incremental matrix . it leverages the second-order derivatives of the loss function to capture weight sensitivity .
Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models struggle with complex reasoning tasks, such as mathematical problem-solving.
Approach: They constructed a symbolic multi-step reasoning task to investigate the information propagation mechanisms in Transformer models when solving the task through direct answering and Chain-of-Thought (CoT) reasoning.
Outcome: The proposed algorithm improves on 7 multi-step reasoning datasets, while introducing only 132 trainable parameters.
The Harmonic Structure of Information Contours (2025.acl-long)

Copied to clipboard

Challenge: Language typically does not maintain a uniform information rate, but it fluctuates around a global average . a new study suggests periodicity may be a factor in information rate oscillations .
Approach: They propose a hypothesis that language does not maintain a uniform information rate . they apply harmonic regression and introduce a new extension to detect periodicity .
Outcome: The proposed method reveals that language oscillates at periodic intervals across frequencies . it also offers a framework for uncovering structural pressures at various levels of linguistic granularity.
HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance (2026.findings-acl)

Copied to clipboard

Challenge: Low-Rank Adaptation (LoRA) assumes a uniform rank r for each incremental matrix, not accounting for the varying significance of weight matrices across modules and layers.
Approach: They propose a framework that allows for faster convergence of low-rank adaptive models . they use a hypernetwork to prune the outputs of the hypernetworks to generate parameters .
Outcome: The proposed framework accelerates convergence of AdaLoRA by leveraging a hypernetwork.
SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have transformed machine learning but have raised significant legal concerns due to their potential to produce text that infringes on copyrights.
Approach: They propose a lightweight, real-time defense mechanism to prevent the generation of copyrighted text by evaluating methods and testing attack strategies.
Outcome: The proposed defense significantly reduces the volume of copyrighted text generated by LLMs by effectively refusing malicious requests.
SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to elicit confidence from large language models are limited to binary or inaccurate group-level confidence estimates.
Approach: They propose a training framework that teaches LLMs to express more fine-grained confidence estimates.
Outcome: The proposed training framework reduces the confidence calibration error and maintains the performance of the model.
Can Language Models Learn Typologically Implausible Languages? (2026.tacl-1)

Copied to clipboard

Challenge: Language models provide a naturalistic framework for studying artificial language learning . authors: typological universals and tendencies are thought to be caused by a learning bias .
Approach: They propose to train LMs on highly naturalistic counterfactual versions of English and Japanese . they show that LM learn subtly implausible languages more slowly .
Outcome: The proposed language models learn subtly implausible languages more slowly compared to human models . the findings suggest that LMs exhibit typologically aligned learning preferences .
Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation (2026.acl-long)

Copied to clipboard

Challenge: Low-Rank Adaptation (LoRA) is a key parameter-efficient fine-tuning method . however, its effectiveness is hampered by semantic drift and structural incoherence .
Approach: They propose a low-rank Adaptation framework that tackles semantic drift and structural incoherence by pruning task-irrelevant directions.
Outcome: Experiments on large language models, vision models, and vision models show that the proposed framework outperforms LoRA and advanced dynamic rank allocation and sparsity-based methods.
Probing for Reading Times (2026.acl-long)

Copied to clipboard

Challenge: a large body of work on probing has demonstrated that language model representations encode a wealth of linguistic information, but it remains unclear whether they also capture cognitive signals about human processing.
Approach: They use regularized linear regression to compare language model representations against scalar predictors.
Outcome: The representations from early layers outperform surprisal in predicting early-pass measures such as first fixation and gaze duration.
DISK: Domain-constrained Instance Sketch for Math Word Problem Generation (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for generating MWP text from equations are inflexible and require pre-defined templates.
Approach: They propose a neural model which generates MWPs from equations by constructing a Quantity Cell Graph from the retrieved MWp instance and reasoning over it.
Outcome: The proposed model performs impressively on educational MWP set and on human evaluation metrics.
Verification-Aware Planning for Multi-Agent Systems (2026.eacl-long)

Copied to clipboard

Challenge: Large language model (LLM) agents are increasingly deployed to tackle complex tasks . multi-agent collaboration introduces new challenges in planning, coordination, and verification .
Approach: They propose a framework for multi-agent collaboration with verification-aware planning . the framework decomposes tasks, models subtask dependencies, and encodes planner-defined passing criteria as subtask verification functions (VFs)
Outcome: The proposed framework outperforms baselines on diverse datasets while improving system robustness and interpretability.
Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data (2025.naacl-long)

Copied to clipboard

Challenge: Contrastive Language-Image Pre-training (CLIP) is a standard for cross-modal image-text representation learning.
Approach: They propose a framework that enhances pre-trained CLIP models by exploiting challenging text-image pairs within existing datasets.
Outcome: The proposed framework improves CLIP models by exploiting text-image pairs in training.
Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models’ Memories (2023.acl-long)

Copied to clipboard

Challenge: Pre-trained language models demonstrate excellent abilities to understand texts in the generic domain while struggling in a specific domain.
Approach: They propose to decouple the feed-forward networks of the Transformer architecture into two parts to maintain old-domain knowledge and a mixture-of-adapters gate to inject domain-specific knowledge in parallel.
Outcome: The proposed method achieves superior performance on in-domain, out-of-domain and knowledge-intensive tasks.
Open-Theatre: An Open-Source Toolkit for LLM-based Interactive Drama (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing tools for creating, modifying, and experimenting with interactive dramas are limited.
Approach: They propose an open-source toolkit for creating configurable LLM-based interactive drama.
Outcome: The proposed toolkit enhances narrative coherence and realistic behavior in interactions with agents.
Cross-Modal Taxonomic Generalization in (Vision-) Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing studies have shown that language models learn from surface form to learn from more grounded evidence.
Approach: They propose to use a vision-language model to learn hypernyms from images . they find that the model can recover this knowledge and generalize even when there is no hypernomia in the image.
Outcome: The proposed model can recover this knowledge and generalize even when the model receives no evidence of hypernyms during training.

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