Search Results for author:
Found 17 papers, 13 papers with code
CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging
In this paper, we introduce CodeSim, a novel multi-agent code generation framework that comprehensively addresses the stages of program synthesis-planning, coding, and debugging-through a human-like perception approach.
Ranked #2 on
Code Generation
on CodeContests
MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models
To bridge this gap, we introduce MapEval, a benchmark designed to assess diverse and complex map-based user queries with geo-spatial reasoning.
Ranked #1 on
Question Answering
on MapEval-API
MapQaTor: A System for Efficient Annotation of Map Query Datasets
Mapping and navigation services like Google Maps, Apple Maps, Openstreet Maps, are essential for accessing various location-based data, yet they often struggle to handle natural language geospatial queries.
VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval
Video Highlight Detection and Moment Retrieval (HD/MR) are essential in video analysis.
Ranked #4 on
Highlight Detection
on QVHighlights
(using extra training data)
Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models
Retrieval-Augmented Generation (RAG) has been shown to enhance the factual accuracy of Large Language Models (LLMs), but existing methods often suffer from limited reasoning capabilities in effectively using the retrieved evidence, particularly when using open-source LLMs.
DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts
Data-driven storytelling is a powerful method for conveying insights by combining narrative techniques with visualizations and text.
A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations
To address this, we systematically review the primary challenges and limitations causing these inconsistencies and unreliable evaluations in various steps of LLM evaluation.
Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis
We identify a number of quality and task-specific issues in the resulting models.
MapCoder: Multi-Agent Code Generation for Competitive Problem Solving
In this paper, we introduce a new approach to code generation tasks leveraging multi-agent prompting that uniquely replicates the full cycle of program synthesis as observed in human developers.
Ranked #1 on
Code Generation
on APPS
(Competition Pass@any metric)
ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning
Further evaluation shows that our instruction-tuning approach supports a wide array of real-world chart comprehension and reasoning scenarios, thereby expanding the scope and applicability of our models to new kinds of tasks.
Evidence to Generate (E2G): A Single-agent Two-step Prompting for Context Grounded and Retrieval Augmented Reasoning
Instead of unverified reasoning claims, this innovative approach leverages the power of "evidence for decision making" by first focusing exclusively on the thought sequences (the series of intermediate steps) explicitly mentioned in the context which then serve as extracted evidence, guiding the LLM's output generation process with greater precision and efficiency.
DelucionQA: Detecting Hallucinations in Domain-specific Question Answering
Hallucination is a well-known phenomenon in text generated by large language models (LLMs).
Learning to Filter Context for Retrieval-Augmented Generation
To alleviate these problems, we propose FILCO, a method that improves the quality of the context provided to the generator by (1) identifying useful context based on lexical and information-theoretic approaches, and (2) training context filtering models that can filter retrieved contexts at test time.
xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval
Recently, pre-trained large language models (LLMs) have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments.
Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies
Prior studies in privacy policies frame the question answering (QA) task as identifying the most relevant text segment or a list of sentences from a policy document given a user query.
Retrieval Augmented Code Generation and Summarization
To mimic developers' code or summary generation behavior, we propose a retrieval augmented framework, REDCODER, that retrieves relevant code or summaries from a retrieval database and provides them as a supplement to code generation or summarization models.
Ranked #1 on
Code Generation
on CodeXGLUE - CodeSearchNet
(using extra training data)
Evaluating the Values of Sources in Transfer Learning
Transfer learning that adapts a model trained on data-rich sources to low-resource targets has been widely applied in natural language processing (NLP).
