Search Results for author:
Found 17 papers, 14 papers with code
An Exploratory Study on Long Dialogue Summarization: What Works and What’s Next
Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series.
Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
These tasks, derived from real-world use cases, evaluate the ability of a multimodal agent to perform data-related tasks by writing code and managing the GUI in enterprise data software systems.
NExT: Teaching Large Language Models to Reason about Code Execution
A fundamental skill among human developers is the ability to understand and reason about program execution.
Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models
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.
L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models
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.
LEVER: Learning to Verify Language-to-Code Generation with Execution
The advent of large language models trained on code (code LLMs) has led to significant progress in language-to-code generation.
Ranked #2 on
Semantic Parsing
on spider
Explicit Knowledge Transfer for Weakly-Supervised Code Generation
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.
FOLIO: Natural Language Reasoning with First-Order Logic
We present FOLIO, a human-annotated, logically complex and diverse dataset for reasoning in natural language (NL), equipped with first-order logic (FOL) annotations.
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions
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.
Ranked #146 on
Arithmetic Reasoning
on GSM8K
Leveraging Locality in Abstractive Text Summarization
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.
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases.
Ranked #1 on
Task-Oriented Dialogue Systems
on KVRET
Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents
To the best of our knowledge, Summ$^N$ is the first multi-stage split-then-summarize framework for long input summarization.
DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization
Transformer-based models have achieved state-of-the-art performance on short-input summarization.
An Exploratory Study on Long Dialogue Summarization: What Works and What's Next
Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series.
SummerTime: Text Summarization Toolkit for Non-experts
We also provide explanations for models and evaluation metrics to help users understand the model behaviors and select models that best suit their needs.
Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization
We also show that retrieval marginalization results in 4. 1 QA F1 improvement over a non-marginalized baseline on HotpotQA in the fullwiki setting.
Merging Weak and Active Supervision for Semantic Parsing
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.
