Papers by Tao Kong

13 papers
UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective (2025.emnlp-main)

Copied to clipboard

Challenge: Deploying large language models (LLMs) for long-context inference remains challenging due to their substantial memory and computational demands.
Approach: They propose an uncertainty-aware framework that leverages truncated matrix entropy to identify areas of low information content.
Outcome: The proposed framework reduces the KV cache size to 4.74% of the original and achieves a 6% speedup.
ProcWorld: Benchmarking Large Model Planning in Reachability-Constrained Environments (2025.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks for embodied spatial reasoning and long-term planning are non-trivial due to the combinatorial complexity of long-horizon abstract reasoning.
Approach: They propose a large-scale benchmark for partially observable embodied spatial reasoning and long-term planning with large language models and vision language models.
Outcome: The proposed model performs better in 16 task types, 5,000 rooms, and over 10 million evaluation trajectories with diverse data distribution.
What Matters in Training a GPT4-Style Language Model with Multimodal Inputs? (2024.naacl-long)

Copied to clipboard

Challenge: Recent advances in GPT-4V have demonstrated remarkable multi-modal capabilities in processing image inputs and following open-ended instructions.
Approach: They propose a plug-and-play technique to enhance multi-modal LLMs . they propose 'lynx' to train multi-modal LLM models .
Outcome: The proposed training strategy improves understanding accuracy and instruction-following proficiency of multi-modal models.
Towards Unifying Reference Expression Generation and Comprehension (2022.emnlp-main)

Copied to clipboard

Challenge: Existing models for REG and REC have distinct inputs and connections between them . a new model for REg and reprehension is needed to solve these problems .
Approach: They propose a unified model for REG and REC that fuses image, region and text . they propose Vision-conditioned Masked Language Modeling and Text-Conditioned Region Prediction .
Outcome: The proposed model outperforms existing models on REG and REC tasks.
ZeroGen: Efficient Zero-shot Learning via Dataset Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to generate training data with pre-trained language models have been found effective in various scenarios.
Approach: They propose an unsupervised zero-shot learning method that generates a dataset from scratch and trains a tiny task model under supervision of the synthesized dataset.
Outcome: The proposed method is annotated-free and efficient, but can provide useful insights from the perspective of data-free model-agnostic knowledge distillation and unreferenced text generation evaluation.
Generating Data for Symbolic Language with Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) bring performance and complexity, but they incur a large computational cost in practice.
Approach: They propose a task-based model which uses large language models to generate symbolic language data by an informative prompt and agreement-based verifier.
Outcome: The proposed model can generate symbolic language data with a few human demonstrations and saves a considerable amount of inference effort.
Bilateral Masking with prompt for Knowledge Graph Completion (2024.findings-naacl)

Copied to clipboard

Challenge: Existing word matching methods fail to obtain satisfactory single embedding representations for entities.
Approach: They propose a bi-encoder-based approach to enhance entity representations by using prompts to narrow the distance between the predicted entity and the known entity.
Outcome: The proposed model achieves state-of-the-art performance on the WN18RR dataset.
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022.emnlp-main)

Copied to clipboard

Challenge: Structured knowledge grounding (SKG) uses structured knowledge to complete user requests . since inputs and outputs of SKG tasks are heterogeneous, they have been studied separately .
Approach: They propose a framework that unifies 21 SKG tasks into a text-to-text format . they use unifiedSKG to benchmark T5 with different sizes .
Outcome: The proposed framework unifies 21 SKG tasks into a text-to-text format . it achieves state-of-the-art performance on almost all of the 21 tasks, the authors show .
MTO: A Multi-turn Conversational Text-to-OverpassQL Dataset for Enhanced OpenStreetMap Query Generation (2026.findings-acl)

Copied to clipboard

Challenge: a framework for constructing multi-turn Text-to-OverpassQL dialogue datasets is proposed . a dataset of over 7,800 dialogues contains more than 20,000 individual utterances .
Approach: They propose a framework for constructing multi-turn Text-to-OverpassQL dialogue datasets . they convert Overpass queries into syntax trees using a custom parser based on OverpassQl .
Outcome: The proposed dataset includes over 7,800 dialogues, each containing 2 to 4 user utterances . it is the first multi-turn Text-to-OverpassQL dataset built upon the OverpassNL corpus .
Textual Dataset Distillation via Language Model Embedding (2024.findings-emnlp)

Copied to clipboard

Challenge: prevailing methods for dataset distillation generate distilled data as embedding vectors, which are not human-readable.
Approach: They propose a model-agnostic, data-efficient method that leverages Language Model embeddings . their method offers enhanced flexibility and improved transferability .
Outcome: The proposed method achieves comparable performance with faster processing times compared to other methods . it offers enhanced flexibility and improved transferability, expanding the range of potential applications .
ImgTrojan: Jailbreaking Vision-Language Models with ONE Image (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies on the safety of large language models (LLMs) with human values have focused on the integration of multi-modal user input into these models.
Approach: They propose a method to bypass safety constraints of large language models by using poisoned images instead of original textual captions.
Outcome: The proposed attack bypasses safety constraints of large language models (VLMs) by replacing the original textual captions with malicious jailbreak prompts.
BPID: A Benchmark for Personal Identity Deduplication (2024.emnlp-industry)

Copied to clipboard

Challenge: Data deduplication is a critical task in data management and mining, focused on consolidating duplicate records that refer to the same entity.
Approach: They propose to use a dataset with 1,000,000 unlabeled synthetic PII profiles and a subset of 10,000 pairs curated and labeled as matches or non-matches.
Outcome: The proposed datasets contain synthetic profiles built from publicly available sources that do not represent real individuals.
ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback (2022.findings-emnlp)

Copied to clipboard

Challenge: Recent work on dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs).
Approach: They propose a progressive zero-shot dataset generation framework which leverages feedback from the task-specific model to guide the generation of new training data via in-context examples.
Outcome: The proposed framework achieves on-par or superior performance with only 1% synthetic dataset size, when compared to baseline methods without in-context feedback.

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