Papers by Lin Gu

35 papers
ANAH: Analytical Annotation of Hallucinations in Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: a comprehensive and fine-grained measurement of the hallucination is crucial for LLMs' wide applications.
Approach: They propose a dataset that offers ANalytical Annotation of Hallucinations in Large Language Models.
Outcome: The proposed dataset can be used to train and evaluate hallucination annotators.
Advancing Vision-Language Models with Adapter Ensemble Strategies (2024.findings-emnlp)

Copied to clipboard

Challenge: CLIP revolutes vision-language pretraining by using contrastive learning on paired web data.
Approach: They propose to combine a "adapter ensemble" with traditional machine learning techniques to augment large-scale pretrained vision-language models.
Outcome: The proposed model outperforms baselines and derives improvement when the number of ensemble parameters increases.
ToolGrad: Efficient Tool-use Dataset Generation with Textual “Gradients” (2026.findings-acl)

Copied to clipboard

Challenge: Prior work synthesizes tool-use LLM datasets by first generating a user query, then complex tool-using annotations like DFS.
Approach: They propose an agentic framework that synthesizes user queries and generates valid tool-use chains . they propose a dataset with more complex tool use, lower cost, and almost 100% pass rate .
Outcome: Experiments show that tools trained on ToolGrad outperform expensive baseline datasets and proprietary LLMs.
Content-Specific Humorous Image Captioning Using Incongruity Resolution Chain-of-Thought (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods for generating humorous captions are generic and do not capture the content of images.
Approach: They propose a framework that generates content-specific resolutions from fine details extracted from an image and integrates logit bias and negative sampling to suppress the output of generic resolutions.
Outcome: The proposed framework generates humorous captions tailored to the content of specific input images.
A Survey on LLM-based Conversational User Simulation (2026.eacl-long)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have enabled high-fidelity generation of synthetic user conversation.
Approach: They propose a taxonomy covering user granularity and simulation objectives . they analyze core techniques and evaluation methodologies to help them understand the latest developments .
Outcome: The proposed model enables high-fidelity generation of synthetic user conversation.
Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for fine-tuning large language models are inefficient and redundant . a light-PEFT framework can be used to prune redundant parameters during training .
Approach: They propose a parameter-efficient fine-tuning framework that freezes most parameters of the foundation model and finetuns only a small number of parameters.
Outcome: The proposed framework achieves training and inference speedup, reduces memory usage, and maintains comparable performance and plug-and-play feature of PEFT.
FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Score (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for detecting out-of-distribution instances are empirical . state-of the-art methods for OOD detection are suboptimal since they only estimate in-distance density pout(x).
Approach: They propose a method that measures the “OOD-ness” of a test case x through the likelihood ratio between out-distribution mathcal Pout and in-division mathcal Pin.
Outcome: The proposed method improves existing methods on popular benchmarks and establishes a new SOTA on popular NLP benchmarks.
Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback (2025.acl-long)

Copied to clipboard

Challenge: Textless Spoken Language Models lag behind text-based Large Language Model (LLM) in semantic coherence and relevance.
Approach: They propose a framework that leverages preference optimization inspired by Reinforcement Learning with Human Feedback to enhance the semantic understanding of SLMs.
Outcome: The proposed framework achieves state-of-the-art performance of SLMs for most benchmarks . it leverages preference optimization inspired by Reinforcement Learning with Human Feedback .
FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing fact-checking evaluation methods rely on static datasets and classification metrics, which fail to evaluate justification production and uncover the nuanced limitations of LLMs.
Approach: They propose a framework that adaptively and dynamically assesses LLMs’ fact-checking capabilities by incorporating justification production alongside verdict prediction.
Outcome: Experiments show that the framework differentiates among state-of-the-art LLMs, providing valuable insights into model strengths and limitations in model-centric fact-checking analysis.
Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs (2025.findings-naacl)

Copied to clipboard

Challenge: Existing watermarking methods embed imperceptible identifiers into text to address copyright concerns.
Approach: They propose a new philosophy for watermark attacks that addresses watermark collision . they demonstrate that collision poses a threat to all logit-based watermark algorithms .
Outcome: The proposed method improves watermark collision performance on top of other methods.
PersLEARN: Research Training through the Lens of Perspective Cultivation (2023.acl-demo)

Copied to clipboard

Challenge: PersLEARN is a tool designed to facilitate the cultivation of scientific perspectives . junior researchers struggle to identify the perspectives reflected in the literature and struggle to develop their own viewpoints.
Approach: They propose a tool to facilitate the cultivation of scientific perspectives by interacting with a prompt-based model and allowing students to develop their own perspectives explicitly.
Outcome: The proposed tool outperforms baseline approaches across multiple domains of literature from different perspectives.
DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence? (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing LLMs' abilities to detect evidence in long contexts are far inferior to humans.
Approach: They propose a benchmark to assess LLMs' abilities in evidence and multi-step commonsense reasoning within a long context.
Outcome: The proposed method improves the performance of LLMs in evidence detection and commonsense reasoning.
BLADE: Benchmarking Language Model Agents for Data-Driven Science (2024.findings-emnlp)

Copied to clipboard

Challenge: Language model-based agents can be used to conduct and support data-driven science, but evaluating them on open-ended tasks is challenging due to multiple valid approaches, partially correct steps, and different ways to express the same decisions.
Approach: They propose a benchmark to automatically evaluate agents’ multifaceted approaches to open-ended research questions.
Outcome: BLADE evaluates agents’ multifaceted approaches to open-ended research questions using data from 12 datasets and research questions drawn from existing scientific literature.
Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods to defend against jailbreak attacks exploit vulnerabilities to elicit unintended or harmful outputs.
Approach: They propose a method to defend against jailbreak attacks by patching specific layers within large language models through self-augmented datasets.
Outcome: The proposed approach reduces harmfulness and attack success rate of jailbreak attacks without compromising utility for benign queries compared to previous methods.
UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents (2026.acl-long)

Copied to clipboard

Challenge: Recent Large Multimodal Models (LMMs) have shown promising potential for performing end-to-end KIE directly from document images.
Approach: They propose a benchmark to evaluate the performance of Large Multimodal Models (LMMs) using a constrained-category KIE track and an open-categorical KIE Track.
Outcome: Experiments on 15 state-of-the-art LMMs show performance degradation under diverse schema definitions, long-tail key fields, and complex layouts, along with pronounced performance disparities across different document types and scenarios.
HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy (2026.acl-industry)

Copied to clipboard

Challenge: relying on large language models for information has raised concerns about reliability and accuracy of outputs.
Approach: They propose a hallucination taxonomy with 11 categories for various NLG tasks and propose HAllucination Detection models which integrate hallucinism detection, span-level identification, and correction into a single inference process.
Outcome: The proposed models outperform baselines on HaluEval, FactCHD, and FaithBench, confirming their robustness and versatility.
ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction (2026.findings-acl)

Copied to clipboard

Challenge: Empirical evaluations on state-of-the-art MLLMs reveal a significant performance gap . ML models lack the fine-grained cross-modal reasoning required to bridge visual discontinuities.
Approach: They propose a benchmark that renders fragmented documents directly from Markdown to facilitate evaluation of VRDU tasks.
Outcome: The proposed benchmark renders fragmented documents directly from Markdown.
DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Chain-of-Thought (CoT) reasoning improves multi-step mathematical problem solving in large language models but is vulnerable to exposure bias and error accumulation.
Approach: They propose a diffusion-styled CoT framework that reformulates CoT reasoning as an iterative denoising process.
Outcome: The proposed framework outperforms existing methods on three multi-step CoT reasoning benchmarks.
DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for reconstruction of large language models overlook diversity among experts, leading to potential redundancy.
Approach: They propose a pruning-based expert reconstruction method that prunes a specific LLM and retrains it on routers, experts and normalization modules.
Outcome: The proposed method outperforms pruning and MoE reconstruction methods on Llama-style models with open-source training corpora.
AutoFigure-Edit: Generating Editable Scientific Illustrations via Reference-Guided Styling (2026.acl-demo)

Copied to clipboard

Challenge: Existing automated systems for scientific illustrations are limited in editability, stylistic controllability, and efficiency.
Approach: They propose an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images.
Outcome: The proposed system generates fully editable scientific illustrations from long-form scientific texts while enabling flexible style adaptation through user-provided reference images.
QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training–Inference Mismatch (2026.findings-acl)

Copied to clipboard

Challenge: Recent work has shown that reinforcement learning with simple rule-based reward functions (RLVR) can induce emergent reasoning behaviors and yield gains in challenging domains such as math problem solving.
Approach: They propose a rollout-alignment-quantization-aware RL which aligns training-side forward with the quantized rollout to minimize mismatch.
Outcome: The proposed approach outperforms quantized-rollout training by +5.5 on Qwen3-30B-A3B MoE for math problems while maintaining low-bit throughput.
SPEAK: Spiking Neurons as an Entropy-Aware Tokenizer for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing tokenizers fail to explicitly leverage historical tokenization results . large language models (LLMs) have demonstrated remarkable effectiveness across NLP tasks .
Approach: They propose a tokenizer that integrates spiking neurons to explicitly leverage historical tokenization results.
Outcome: The proposed tokenizer leverages historical tokenization results, but does not selectively leverage history based on contextual relevance.
Weights-Rotated Preference Optimization for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods to align large language models with high reward hacking are limited by the complexity of the parameter space and the complexity.
Approach: They propose a weights-rotated preference optimization algorithm that constrains the output layer logits with the KL divergence inherited from DPO and fine-tunes the intermediate hidden states.
Outcome: The proposed algorithm achieves a 3.27-point improvement on AlpacaEval 2 and surpasses the best baseline by 6.2 to 7.5 points on MT-Bench with merely 0.015% of the trainable parameters.
UEGP: Unified Expert-Guided Pre-training for Knowledge Rekindle (2024.findings-naacl)

Copied to clipboard

Challenge: Existing paradigms for pre-training and fine-tuning have limitations . knowledge rekindle aims to break through performance upper bounds of experts without introducing additional annotated data.
Approach: They propose a new paradigm for pre-training and fine-tuning that aims to re-incorporate the fine- tuned expert model into the training cycle and break through performance upper bounds of experts.
Outcome: The proposed model breaks through performance upper bounds of experts without additional annotated data.
Language Modeling with Sparse Product of Sememe Experts (D18-1)

Copied to clipboard

Challenge: Existing language modeling methods rely on large-scale text data to learn the sequential patterns of words.
Approach: They propose to use sememes to represent the implicit semantics behind words for language modeling . they propose to employ sememe-driven language models to fine-grained semem-level semantics .
Outcome: Experiments on language modeling and the downstream application of headline generation show the effectiveness of SDLM.
HoWToBench: Holistic Evaluation for LLM’s Capability in Human-level Writing using Tree of Writing (2026.acl-long)

Copied to clipboard

Challenge: Evaluating the writing capabilities of large language models remains a significant challenge due to the multidimensional nature of writing skills and the limitations of existing metrics.
Approach: They propose to model the aggregation weights of sub-features in a tree-structured workflow and propose a Chinese writing benchmark that mitigates biases.
Outcome: The proposed tree-of-writing (ToW) measures the writing capabilities of large language models (LLMs) in Chinese and shows that it mitigates biases and achieves a *0.93* Pearson correlation with human judgments.
A Gradient Control Method for Backdoor Attacks on Parameter-Efficient Tuning (2023.acl-long)

Copied to clipboard

Challenge: Parameter-Efficient Tuning (PET) fine-tunes pre-trained language models for downstream tasks, but a large reduction in the number of attackable parameters will greatly affect the effectiveness of backdoor attacks, resulting in backdoor forgetting.
Approach: They propose a gradient control method to consolidate the attack effect by freezing most parameters of the pre-trained model and fine-tuning only a small number of parameters.
Outcome: The proposed method improves sentiment classification and spam detection, and can be applied to different tasks.
Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models (2025.acl-long)

Copied to clipboard

Challenge: Parameter-efficient fine-tuning (PEFT) is a common method for fine- tuning large language models . however, once updated, PEFT modules suffer performance degradation on newer versions .
Approach: They propose a method that enhances the PEFT module by focusing on the task-specific pattern while reducing its dependence on certain knowledge in the base model.
Outcome: Experiments show that PEFT modules can maintain performance on updated models without re-tuning . the proposed approach can be used in real-world applications with large model sizes .
HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs (2026.findings-acl)

Copied to clipboard

Challenge: High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly.
Approach: They define the first HSS domain system covering 14 mainstream fields and introduce HSS-Synth.
Outcome: the proposed pipeline outperforms 14 leading baselines on 16 benchmarks.
Learning Dynamic Context Augmentation for Global Entity Linking (D19-1)

Copied to clipboard

Challenge: Existing collective entity linking methods are expensive and often lack local context information.
Approach: They propose a dynamic context-augmented inference model that can be used to make collective inference.
Outcome: The proposed model can cope with different local EL models with different learning settings, base models, decision orders and attention mechanisms.
BeamLoRA: Beam-Constraint Low-Rank Adaptation (2025.acl-long)

Copied to clipboard

Challenge: Low-Rank Adaptation (LoRA) is one of the most efficient parameter-efficient fine-tuning methods.
Approach: They propose to conceptualize each LoRA module as a beam where each rank corresponds to a potential sub-solution.
Outcome: The proposed method improves performance on three base models and 12 datasets.
Fair Text-Attributed Graph Representation Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Text-Attributed Graphs (TAGs) inherit issues from Graph Neural Networks such as fairness.
Approach: They propose to evolve LM-as-encoder to LM as-fair-encoding process to explore fairness in TAGRL.
Outcome: The proposed process can be integrated with fairness-enhancing strategies on the GNNs decoder side.
CBP-Tuning: Efficient Local Customization for Black-box Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Customized black-box prompt tuning is a new approach to customize large language models . however, as models grow, the resources required for training and deployment become increasingly expensive .
Approach: They propose a framework that facilitates efficient local customization while preserving bidirectional privacy.
Outcome: The proposed framework facilitates efficient local customization while preserving bidirectional privacy.
IntelliCockpitBench: A Comprehensive Benchmark to Evaluate VLMs for Intelligent Cockpit (2025.findings-acl)

Copied to clipboard

Challenge: Visual Question Answering (VQA) is a key task in vehicular systems.
Approach: They propose a benchmark that encompasses diverse automotive scenarios . they use images from front, side, and rear cameras, various road types, weather conditions, and interior views .
Outcome: The proposed benchmark includes images from front, side, and rear cameras, various road types, weather conditions, and interior views.

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