Search Results for author: Ansong Ni

Found 15 papers, 13 papers with code

Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models

1 code implementation6 Mar 2024 Martin Riddell, Ansong Ni, Arman Cohan

While large language models have achieved remarkable performance on various code generation benchmarks, there have been growing concerns regarding potential contamination of these benchmarks as they may be leaked into pretraining and finetuning data.

Code Generation Memorization +1

L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models

no code implementations29 Sep 2023 Ansong Ni, Pengcheng Yin, Yilun Zhao, Martin Riddell, Troy Feng, Rui Shen, Stephen Yin, Ye Liu, Semih Yavuz, Caiming Xiong, Shafiq Joty, Yingbo Zhou, Dragomir Radev, Arman Cohan

Recently, large language models (LLMs), especially those that are pretrained on code, have demonstrated strong capabilities in generating programs from natural language inputs in a few-shot or even zero-shot manner.

Code Generation Math +1

LEVER: Learning to Verify Language-to-Code Generation with Execution

1 code implementation16 Feb 2023 Ansong Ni, Srini Iyer, Dragomir Radev, Ves Stoyanov, Wen-tau Yih, Sida I. Wang, Xi Victoria Lin

The advent of large language models trained on code (code LLMs) has led to significant progress in language-to-code generation.

Arithmetic Reasoning Code Generation +3

Explicit Knowledge Transfer for Weakly-Supervised Code Generation

no code implementations30 Nov 2022 Zhangir Azerbayev, Ansong Ni, Hailey Schoelkopf, Dragomir Radev

More specifically, we propose explicit knowledge transfer (EKT), which uses the few-shot capabilities of a teacher LLM to create NL-code pairs that we then filter for correctness and fine-tune the student on.

Code Generation Few-Shot Learning +4

Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions

1 code implementation28 May 2022 Ansong Ni, Jeevana Priya Inala, Chenglong Wang, Oleksandr Polozov, Christopher Meek, Dragomir Radev, Jianfeng Gao

We show that our use of self-sampled correct and partially-correct solutions can benefit learning and help guide the sampling process, leading to more efficient exploration of the solution space.

Arithmetic Reasoning Efficient Exploration +3

Leveraging Locality in Abstractive Text Summarization

1 code implementation25 May 2022 Yixin Liu, Ansong Ni, Linyong Nan, Budhaditya Deb, Chenguang Zhu, Ahmed H. Awadallah, Dragomir Radev

Our experimental results show that our model has a better performance compared with strong baselines with efficient attention modules, and our analysis provides further insights into our locality-aware modeling strategy.

Abstractive Text Summarization Text Generation

An Exploratory Study on Long Dialogue Summarization: What Works and What's Next

1 code implementation10 Sep 2021 Yusen Zhang, Ansong Ni, Tao Yu, Rui Zhang, Chenguang Zhu, Budhaditya Deb, Asli Celikyilmaz, Ahmed Hassan Awadallah, Dragomir Radev

Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series.

Retrieval

SummerTime: Text Summarization Toolkit for Non-experts

1 code implementation EMNLP (ACL) 2021 Ansong Ni, Zhangir Azerbayev, Mutethia Mutuma, Troy Feng, Yusen Zhang, Tao Yu, Ahmed Hassan Awadallah, Dragomir Radev

We also provide explanations for models and evaluation metrics to help users understand the model behaviors and select models that best suit their needs.

Document Summarization Multi-Document Summarization

Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization

1 code implementation EMNLP 2021 Ansong Ni, Matt Gardner, Pradeep Dasigi

We also show that retrieval marginalization results in 4. 1 QA F1 improvement over a non-marginalized baseline on HotpotQA in the fullwiki setting.

Question Answering Retrieval

Merging Weak and Active Supervision for Semantic Parsing

1 code implementation29 Nov 2019 Ansong Ni, Pengcheng Yin, Graham Neubig

Experiments on WikiTableQuestions with human annotators show that our method can improve the performance with only 100 active queries, especially for weakly-supervised parsers learnt from a cold start.

Active Learning Semantic Parsing

Cannot find the paper you are looking for? You can Submit a new open access paper.