Papers by Cui Ding

22 papers
RepoDistill: Distilling Repository Knowledge through Compression-Aware Budget Allocation and Policy Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have strong performance on code translation tasks, but they struggle with repository-level scenarios where context is extensive and interdependent.
Approach: They propose a framework that integrates retrieval with learning budget allocation for fine-grained context compression.
Outcome: The proposed framework outperforms baselines on SWE-QA, CoderEval, and LongCodeU.
Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have advanced natural language processing, but their effectiveness is often hampered by parameter mis-filling during tool calling.
Approach: They propose a hierarchical tool error checklist framework to diagnose and mitigate tool-calling errors without relying on extensive real-world interactions.
Outcome: The proposed framework improves parameter-filling accuracy and tool-calling success rates compared to baseline methods.
Few-shot Classification with Hypersphere Modeling of Prototypes (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for fewshot learning use embeddings in space, but they lack expressivity and are difficult to perform statistically.
Approach: They propose a method where class information is represented by hyperspheres with dynamic sizes with two sets of learnable parameters: the hypersphere’s center and the radius.
Outcome: The proposed method is much more expressive than embeddings and performs better than statistical modeling.
Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to review scientific papers are limited by their content or quality . SEA is a framework for automated scientific review, but its contents are generic or partial.
Approach: They propose a framework for automated scientific review using large language models . they propose to use a standardized review dataset to fine-tune an LLM to generate high-quality reviews.
Outcome: The proposed framework can generate high-quality reviews from standardized datasets and improves on the existing feedback mechanisms.
Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment (2024.emnlp-main)

Copied to clipboard

Challenge: Existing algorithms for achieving optimal alignment are mostly unidirectional . a recent study suggests that large language models can be ground with evident preferences .
Approach: They propose to ground large language models with evident preferences . they propose to use controllable preference optimization to specify different objectives .
Outcome: The proposed models can provide responses that match various preferences among the ”3H” desiderata.
A Novel Matching Paradigm: Unified Generative and Discriminative LLM with Prompt Compression for Relevance Learning (2026.acl-industry)

Copied to clipboard

Challenge: Existing approaches to matching use Large Language Models as feature extractors, underutilizing their full modeling capabilities.
Approach: They propose a matching paradigm that integrates two-tower, single-towing, and generative tasks within a unified LLM framework via attention-mask partitioning.
Outcome: The proposed model achieves superior performance and strong practical value in an industrial search engine.
ConLoan: A Contrastive Multilingual Dataset for Evaluating Loanwords (2025.acl-long)

Copied to clipboard

Challenge: Lexical borrowing is a ubiquitous linguistic phenomenon influenced by geopolitical, societal, and technological factors.
Approach: They propose a novel contrastive dataset comprising sentences with and without loanwords across 10 languages to examine how machine translation and language models process loanword .
Outcome: The proposed dataset shows that state-of-the-art models prefer loanwords over native terms and exhibit varying performance across languages.
Fusing Highly Specialized Language Models for Comprehensive Expertise (2025.acl-long)

Copied to clipboard

Challenge: Existing models that focus on language, programming code, and mathematical symbols are not able to achieve mastery of all three domains simultaneously.
Approach: They propose to fuse highly-specialized models that are already sufficiently trained on different domains to achieve a highly-specific model.
Outcome: The proposed model could achieve mastery of the three crucial domains simultaneously.
Decoder Tuning: Efficient Language Understanding as Decoding (2023.acl-long)

Copied to clipboard

Challenge: Existing approaches to adapt pre-trained models with parameters frozen are based on input-side adaptation, which requires thousands of API queries.
Approach: They propose to train a model-as-a-service (MaaS) setting to provide only the inference APIs for users . they argue that input-side adaptation could be arduous due to the lack of gradient signals .
Outcome: The proposed model outperforms state-of-the-art algorithms with a 200x speed-up.
INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair (2024.findings-acl)

Copied to clipboard

Challenge: Experimental results show that INTERVENOR surpasses baseline models, exhibiting improvements of approximately 18% and 4.3% over GPT-3.5 in code generation and code translation tasks.
Approach: They propose a system that prompts Large Language Models to play distinct roles during the code repair process, functioning as both a Code Learner and a code teacher.
Outcome: The proposed system surpasses baseline models in code generation and code translation tasks and improves on syntax errors and assertion errors.
Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies have found that low-rank pre-training often compromises effectiveness.
Approach: They propose to apply low-dimensional module only to the attention layer to improve both effectiveness and efficiency.
Outcome: The proposed model saves 12.4% time while improving test perplexity and on downstream tasks compared with vanilla Transformer.
The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning (2025.findings-acl)

Copied to clipboard

Challenge: Existing work on instruction tuning has focused on task level, without considering that tasks are artificially defined and, to LLMs, merely consist of tokens and representations.
Approach: They propose a training data arrangement framework that allows for continual learning and loss reduction.
Outcome: The proposed framework promotes continual learning and loss reduction on unseen tasks.
V-GameGym: Visual Game Generation for Code Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing code-related benchmarks focus on single modality rather than visual game development.
Approach: They propose a multimodal benchmark for evaluating code large language models in visual game generation that integrates a clustering-based curation methodology and a pipeline for visual code synthesis.
Outcome: The proposed framework assesses code generation and visual game generation using a sandbox environment.
Prototypical Verbalizer for Prompt-based Few-shot Tuning (2022.acl-long)

Copied to clipboard

Challenge: Prompt-based tuning for pre-trained language models has shown its effectiveness in few-shot learning.
Approach: They propose a prototypical verbalizer which learns prototype vectors as verbalizes by contrastive learning.
Outcome: The proposed verbalizer outperforms existing verbalizing methods on topic classification and entity typing tasks.
Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for embodied reasoning are coarse-grained and expensive . branch-and-browse framework enables fine-grounded, memory-guided, and efficient multi-branch reasoning.
Approach: They propose a framework that unifies structured reasoning-acting, contextual memory, and efficient execution.
Outcome: The proposed framework achieves task success rate of 35.8% and reduces execution time by up to 40.4% relative to state-of-the-art methods.
Using Information Theory to Characterize Prosodic Typology: The Case of Tone, Pitch-Accent and Stress-Accent (2025.acl-long)

Copied to clipboard

Challenge: lexical identity and prosody are well-studied parameters of linguistic variation, but they are difficult to predict in tonal languages.
Approach: They propose to characterize the relationship between lexical identity and prosody using information theory to estimate mutual information between the text and pitch curves.
Outcome: The proposed hypothesis supports perspectives that view linguistic typology as gradient, rather than categorical.
UltraIF: Advancing Instruction Following from the Wild (2025.emnlp-main)

Copied to clipboard

Challenge: a lack of transparency has resulted in a gap between research community and leading companies . large language models have demonstrated remarkable capabilities in following complex instructions .
Approach: They propose a method to build large language models that can follow complex instructions with open-source data.
Outcome: The proposed approach can synergize complex instructions and filter responses with evaluation questions.
Self-Evolving GPT: A Lifelong Autonomous Experiential Learner (2024.acl-long)

Copied to clipboard

Challenge: Existing approaches to provide LLMs with textual task-solving experience rely on manual efforts to acquire and apply such experience for each task.
Approach: They propose a lifelong autonomous experiential learning framework based on LLMs that learns and accumulates experience through experience transfer and induction.
Outcome: The proposed framework performs reliably in each intermediate step and improves GPT-3.5 and GPT-4 on widely used NLP datasets.
Retrieval Heads are Dynamic (2026.acl-long)

Copied to clipboard

Challenge: Recent studies have identified "retrieval heads" in Large Language Models responsible for extracting information from input contexts.
Approach: They propose to examine retrieval heads from a dynamic perspective . they establish that retrieval head activation is highly dynamic and functionally irreplaceable .
Outcome: The proposed model's hidden state encodes a predictive signal for future retrieval head patterns, indicating an internal planning mechanism.
Modeling Bottom-up Information Quality during Language Processing (2025.emnlp-main)

Copied to clipboard

Challenge: Contemporary theories of language processing model language processing as integrating both top-down expectations and bottom-up inputs.
Approach: They propose an information-theoretic operationalization for the “quality” of bottom-up information as the mutual information between visual information and word identity.
Outcome: The proposed model compares reading times in English and Chinese in which words' information quality has been reduced by occluding their top or bottom half with full words.
Boosting LLM’s Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Molecular structure elucidation involves deducing a molecule’s structure from various types of spectral data, which is crucial in chemical experimental analysis.
Approach: They propose a Knowledge-enhanced reasoning framework for Molecular Structure Elucidation that leverages Monte Carlo Tree Search for test-time scaling as a plugin to extend the LLMs’ coverage of the chemical structure space.
Outcome: The proposed framework significantly improves on both GPT-4o-mini and GPT4o, and a specialized molecule-spectrum scorer improves performance.
Improving Multi-task Stance Detection with Multi-task Interaction Network (2022.emnlp-main)

Copied to clipboard

Challenge: Recent studies have proposed multi-task learning models that introduce sentiment information to boost stance detection but neglect to capture the fine-grained task-specific interaction between stance and sentiment tasks, thus degrading performance.
Approach: They propose a novel multi-task interaction network (MTIN) that captures the word-level interaction between tasks, so as to obtain richer task representations.
Outcome: The proposed approach outperforms state-of-the-art methods on two real-world 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