Papers by Dianbo Liu

22 papers
To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing unlearning paradigms are mired in vague forgetting boundaries, erasing knowledge indiscriminately.
Approach: They propose a benchmark to evaluate if unlearning erases essential knowledge . they propose 'knowUnDo' which uses copyrighted content and privacy domains .
Outcome: The proposed method is superior to existing methods in both precise knowledge unlearning and general knowledge retaining of LLMs.
Set Generation Networks for End-to-End Knowledge Base Population (2021.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge base population systems require a machine translation task to generate multiple facts, but the fact order is not considered.
Approach: They propose a knowledge base population task that aims to discover facts about entities from texts and expand a KB with these facts.
Outcome: The proposed networks achieve state-of-the-art (SoTA) performance on two benchmark datasets.
Analyzing Chain-of-thought Prompting in Black-Box Large Language Models via Estimated V-information (2024.lrec-main)

Copied to clipboard

Challenge: Chain-of-Thought (CoT) prompting and large language models (LLMs) have shown great potential in improving performance on challenging reasoning tasks.
Approach: They propose a new metric which extends the concept of pointwise V-information to black-box models and quantifies label-relevant new information introduced by CoT prompting.
Outcome: The proposed metric extends the concept of pointwise V-information to black-box models, quantifying label-relevant new information introduced by CoT prompting beyond pre-existing label information.
Novel Relation Detection: Discovering Unknown Relation Types via Multi-Strategy Self-Supervised Learning (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to relation extraction can only recognize predefined relation types . new or out-of-scope relation types may continually emerge after the model is deployed .
Approach: They propose a novel relation detection task that uses self-supervised learning to handle shallow semantic similarity problem.
Outcome: The proposed method outperforms state-of-the-art methods on two datasets.
Distantly Supervised Relation Extraction in Federated Settings (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to label training datasets using distant supervision are expensive and cannot cover all walks of life.
Approach: They propose a federated denoising framework to suppress label noise in federation . they propose to use a multiple instance learning based denoisation method to select reliable sentences .
Outcome: The proposed method can select reliable sentences via cross-platform collaboration.
Editing the Moving World: Model Editing for Video LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing models for knowledge editing focus on knowledge-level or static visual domains, overlooking dynamic semantics.
Approach: They propose a benchmark for modeling large language models using six representative models . they analyze the strengths and limitations of existing models and identify new directions .
Outcome: The proposed benchmark extends existing models from static modalities to dynamic video scenarios.
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for parameter pruning fail to utilize the knowledge from pruned parameters.
Approach: They propose a method that uses manifold learning and the Information Bottleneck measure to merge similar layers to preserve model performance.
Outcome: The proposed method outperforms pruning methods on multiple datasets and LLMs with quantization and achieves substantial compression ratios.
A Large-Scale Chinese Multimodal NER Dataset with Speech Clues (2021.acl-long)

Copied to clipboard

Challenge: Using a large-scale dataset, we explore Chinese named entity recognition (NER) with both textual and acoustic contents.
Approach: They propose a Chinese multimodal named entity recognition dataset . their corpus contains 42,987 annotated sentences and 71 hours of speech data .
Outcome: The proposed model yields state-of-the-art (SoTA) results on Chinese multimodal named entity recognition (NER) based on 42,987 annotated sentences and 71 hours of speech data.
ScEdit: Script-based Assessment of Knowledge Editing (2025.findings-acl)

Copied to clipboard

Challenge: Knowledge Editing (KE) has gained increasing attention, yet current evaluation frameworks do not integrate KE into real-world application scenarios.
Approach: They propose a script-based benchmark which encompasses both counterfactual and temporal edits and integrates token-level and text-level evaluation methods.
Outcome: The proposed method combines token-level and text-level evaluation methods with a new fact-based evaluation framework.
Learning with Partial Annotations for Event Detection (2023.acl-long)

Copied to clipboard

Challenge: Event detection (ED) requires fully labeled and high-quality training data.
Approach: They propose a new trigger localization formulation using contrastive learning to distinguish ground-truth triggers from contexts and show a decent robustness for addressing partial annotation noise.
Outcome: The proposed approach achieves an F1 score of over 60% in an extreme scenario where 90% of events are unlabeled.
Class Lifelong Learning for Intent Detection via Structure Consolidation Networks (2023.findings-acl)

Copied to clipboard

Challenge: Existing intent detection models can only handle predefined intent classes in the offline environment.
Approach: They propose a method that continually learns new intent classes from new data . structure-based retrospection and contrastive knowledge distillation are used to solve these problems .
Outcome: The proposed method outperforms existing models on three benchmarks.
Exploring Deductive and Inductive Reasoning Capabilities of Large Language Models in Procedural Planning (2025.findings-emnlp)

Copied to clipboard

Challenge: Deductive and inductive reasoning are fundamental components of human cognition . authors present a benchmark to assess their performance in procedural planning .
Approach: They propose a benchmark to assess the deductive and inductive reasoning abilities of LLMs . they propose IMSE to enable LLM to generate multiple similar procedural plans .
Outcome: The proposed method improves inductive reasoning abilities of LLMs, the authors show . they show that LLM models show excellent deductive reasoning capabilities but suboptimal inductive performance.
Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network (D19-1)

Copied to clipboard

Challenge: Existing models for named entity recognition (NER) lack word boundaries information, which is a major barrier to developing a high performance named entity system.
Approach: They propose a Chinese named entity recognition system with word boundaries information . they use word-level representations and character-level models to integrate lexical knowledge into Chinese NER .
Outcome: The proposed model outperforms the state-of-the-art model and achieves a speed of up to 15 times faster than the SOTA model.
Document-level Event Extraction via Parallel Prediction Networks (2021.acl-long)

Copied to clipboard

Challenge: Document-level event extraction (DEE) is indispensable when events are described throughout a document.
Approach: They propose a document-level event extraction model that can extract structured events from a text in parallel.
Outcome: The proposed model outperforms current state-of-the-art methods on a document-level event extraction task.
SHARP: Steering Hallucination in LVLMs via Representation Engineering (2025.emnlp-main)

Copied to clipboard

Challenge: Large Vision-Language Models (LVLMs) generate responses that are plausible but incorrect or unsupported—commonly referred to as hallucinations.
Approach: They propose a representation-level intervention framework that modulates hallucination-related features during inference by probing their encoded features.
Outcome: The proposed framework reduces hallucinations while maintaining the performance and generalization capabilities of Large Vision-Language Models (LVLMs).
Decoupling Generalization and Adaptation in Meta-Learning for Large Language Models (2026.acl-short)

Copied to clipboard

Challenge: Adapting large language models to specific downstream tasks requires multi-step fine-tuning with substantial training data, incurring significant computational overhead.
Approach: They propose a framework that separates learning generalizable initializations and adaptation through dedicated parameter spaces.
Outcome: The proposed framework outperforms existing meta-learning and standard multi-task baselines on common-sense reasoning, mathematics, logic, medical and coding benchmarks.
UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing LLMs demonstrate powerful capabilities between tasks, but can they make sequential decisions?
Approach: They propose to evaluate sequential decision-making capability of large language models (LLMs) using novel metrics based Monte Carlo methods.
Outcome: The proposed benchmark improves sequential decision-making performance compared to the vanilla LLM player.
A Framework for Effective Invocation Methods of Various LLM Services (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are becoming a fundamental tool for various natural language processing tasks due to commercial reasons, the potential risk of misuse and expensive tuning cost.
Approach: They propose a framework for constructing an effective LLM services invocation strategy that best meets task demands.
Outcome: The proposed framework classifies existing methods into four categories: input abstraction, semantic cache, solution design, and output enhancement, which can be used separately or jointly during the invocation life cycle.
Knowledge Guided Metric Learning for Few-Shot Text Classification (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods to learn from limited examples are insufficient for many-shot text classification tasks.
Approach: They propose to introduce external knowledge into few-shot learning to imitate human knowledge by creating a parameter generator network that generates different metrics for different tasks.
Outcome: The proposed method outperforms the SoTA few-shot text classification models.
Graph-Based Knowledge Integration for Question Answering over Dialogue (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches for question answering over dialogue did not consider dialogue structure and background knowledge (e.g., relationships between speakers).
Approach: They propose a method which organizes a dialogue as a "relational graph" and uses edges to represent relationships between entities to encode multi-relations knowledge for reasoning.
Outcome: The proposed method is better at tackling complex questions requiring relational reasoning and defending adversarial attacks with distracting sentences.
M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model (2025.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge editing methods for MLLMs lack multi-granularity knowledge . existing knowledge editing approaches lack multimodality knowledge and generalize to multimodal data.
Approach: They propose a multimodal knowledge editing method which integrates key knowledge layers within MLLMs and collaboratively edits them.
Outcome: The proposed method improves visual generality performance on knowledge data of different granularities.
Representative Demonstration Selection for In-Context Learning with Two-Stage Determinantal Point Process (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods tend to select different demonstrations for each test instance, which is time-consuming and poses limitations in practical scenarios.
Approach: They propose to select a representative subset of in-context demonstrations that can prompt different test instances in a specific task.
Outcome: The proposed method can be used to generate representative in-context demonstrations.

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