Search Results for author:
Found 27 papers, 17 papers with code
Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute
Recent advancements in software engineering agents have demonstrated promising capabilities in automating program improvements.
Do Code LLMs Understand Design Patterns?
Code Large Language Models (LLMs) demonstrate great versatility in adapting to various downstream tasks, including code generation and completion, as well as bug detection and fixing.
LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues
Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem.
Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement
The results demonstrate that Lingma SWE-GPT 72B successfully resolves 30. 20% of the GitHub issues, marking a significant improvement in automatic issue resolution (22. 76% relative improvement compared to Llama 3. 1 405B), approaching the performance of closed-source models (31. 80\% issues of GPT-4o resolved).
EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
These evaluations help practitioners select superior LLMs in specific domains and discover the shortcomings of existing LLMs.
Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?
Code completion, a key downstream task in code generation, is one of the most frequent and impactful methods for enhancing developer productivity in software development.
In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks
To address this, inspired by transfer learning, we propose In-Context Transfer Learning (ICTL), which synthesizes target task demonstrations by transferring labeled demonstrations from similar source tasks.
Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
Experimental results indicate that our largest agent, with 150 million parameters, achieves 78. 9% human-level performance on pretrained games using only 10% subsampled offline data, outperforming existing state-of-the-art large-scale offline RL baselines by 31. 6% on averange.
Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration
This paper presents Alibaba LingmaAgent, a novel Automated Software Engineering method designed to comprehensively understand and utilize whole software repositories for issue resolution.
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories
Our experiments reveal these LLMs' coding abilities in real-world code repositories.
Unifying Structured Data as Graph for Data-to-Text Pre-Training
In this paper, we unify different types of structured data (i. e., table, key-value data, knowledge graph) into the graph format and cast different data-to-text generation tasks as graph-to-text generation.
CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality
To alleviate these limitations, in this paper, we present CATS, a pragmatic Chinese answer-to-sequence dataset with large scale and high quality.
History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling
Context information modeling is an important task in conversational KBQA.
Iterative Forward Tuning Boosts In-Context Learning in Language Models
Despite the advancements in in-context learning (ICL) for large language models (LLMs), current research centers on specific prompt engineering, such as demonstration selection, with the expectation that a single iteration of demonstrations processing can generalize effectively to a given test sample.
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
Our emphasis on database values highlights the new challenges of dirty database contents, external knowledge between NL questions and database contents, and SQL efficiency, particularly in the context of massive databases.
Ranked #1 on
Text-To-SQL
on BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)
(Execution Accurarcy (Human) metric)
Plan-then-Seam: Towards Efficient Table-to-Text Generation
Table-to-text generation aims at automatically generating text to help people conveniently obtain salient information in tables.
Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning
To alleviate the above challenges, we exploit large language models (LLMs) as decomposers for effective table-based reasoning, which (i) decompose huge evidence (a huge table) into sub-evidence (a small table) to mitigate the interference of useless information for table reasoning; and (ii) decompose complex questions into simpler sub-questions for text reasoning.
Ranked #2 on
Table-based Fact Verification
on TabFact
Towards Generalizable and Robust Text-to-SQL Parsing
Text-to-SQL parsing tackles the problem of mapping natural language questions to executable SQL queries.
STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing
Concretely, we propose two novel pre-training objectives which respectively explore the context-dependent interactions of NL utterances and SQL queries within each text-to-SQL conversation: (i) schema state tracking (SST) objective that tracks and explores the schema states of context-dependent SQL queries in the form of schema-states by predicting and updating the value of each schema slot during interaction; (ii) utterance dependency tracking (UDT) objective that employs weighted contrastive learning to pull together two semantically similar NL utterances and push away the representations of semantically dissimilar NL utterances within each conversation.
Graph-to-Text Generation with Dynamic Structure Pruning
Most graph-to-text works are built on the encoder-decoder framework with cross-attention mechanism.
SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers
To improve the generalizability and stability of neural text-to-SQL parsers, we propose a model uncertainty constraint to refine the query representations by enforcing the output representations of different perturbed encoding networks to be consistent with each other.
A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions
In recent years, deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output SQL query.
Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing
The importance of building text-to-SQL parsers which can be applied to new databases has long been acknowledged, and a critical step to achieve this goal is schema linking, i. e., properly recognizing mentions of unseen columns or tables when generating SQLs.
Improving Text-to-SQL with Schema Dependency Learning
In this paper, we present the Schema Dependency guided multi-task Text-to-SQL model (SDSQL) to guide the network to effectively capture the interactions between questions and schemas.
Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
Semantic parsing has long been a fundamental problem in natural language processing.
Ranked #5 on
Dialogue State Tracking
on CoSQL
Dynamic Memory Induction Networks for Few-Shot Text Classification
This paper proposes Dynamic Memory Induction Networks (DMIN) for few-shot text classification.
Induction Networks for Few-Shot Text Classification
Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries.
Ranked #1 on
Few-Shot Text Classification
on ODIC 5-way (10-shot)
