Search Results for author:
Found 20 papers, 13 papers with code
Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving
The task of issue resolving is to modify a codebase to generate a patch that addresses a given issue.
CodeV: Issue Resolving with Visual Data
Large Language Models (LLMs) have advanced rapidly in recent years, with their applications in software engineering expanding to more complex repository-level tasks.
Aligning CodeLLMs with Direct Preference Optimization
We also contribute a pipeline for collecting preference pairs for DPO on CodeLLMs.
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
However, existing benchmarks like GSM8K or MATH are now being solved with high accuracy (e. g., OpenAI o1 achieves 94. 8\% on MATH dataset), indicating their inadequacy for truly challenging these models.
Elephant in the Room: Unveiling the Impact of Reward Model Quality in Alignment
Despite the vital role reward models play in alignment, previous works have consistently overlooked their performance and used off-the-shelf reward models arbitrarily without verification, rendering the reward model ``\emph{an elephant in the room}''.
Towards a Unified View of Preference Learning for Large Language Models: A Survey
Finally, based on our unified perspective, we explore the challenges and future research directions for aligning large language models with human preferences.
SWE-bench-java: A GitHub Issue Resolving Benchmark for Java
GitHub issue resolving is a critical task in software engineering, recently gaining significant attention in both industry and academia.
The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models
As a result, previous debiasing methods mainly finetune or even pre-train language models on newly constructed anti-stereotypical datasets, which are high-cost.
CodeR: Issue Resolving with Multi-Agent and Task Graphs
GitHub issue resolving recently has attracted significant attention from academia and industry.
Ranked #1 on
Bug fixing
on SWE-bench-lite
CodeS: Natural Language to Code Repository via Multi-Layer Sketch
For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies.
Improving Natural Language Capability of Code Large Language Model
Code large language models (Code LLMs) have demonstrated remarkable performance in code generation.
A GAN-based data poisoning framework against anomaly detection in vertical federated learning
Specifically, the malicious participant initially employs semi-supervised learning to train a surrogate target model.
Can Programming Languages Boost Each Other via Instruction Tuning?
Results demonstrate that programming languages can significantly improve each other.
PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
In this paper, we propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation.
Hierarchical and Contrastive Representation Learning for Knowledge-aware Recommendation
Specifically, for avoiding the exponential expansion of neighbors, we propose a hierarchical message aggregation mechanism to interact separately with low-order neighbors and meta-path-constrained high-order neighbors.
RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation
The task of repository-level code completion is to continue writing the unfinished code based on a broader context of the repository.
Ranked #2 on
Code Completion
on Rambo Benchmark
Large Language Models Meet NL2Code: A Survey
The task of generating code from a natural language description, or NL2Code, is considered a pressing and significant challenge in code intelligence.
When Language Model Meets Private Library
In this paper, we investigate how to equip pre-trained language models with the ability of code generation for private libraries.
CodeT: Code Generation with Generated Tests
A natural way to evaluate the quality and correctness of a code solution is to run it against a set of test cases, but the manual creation of such test cases is often costly and time-consuming.
Ranked #4 on
Code Generation
on APPS
CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation
Usually, expensive text-code paired data is essential for training a code generation model.
