Search Results for author: Kexun Zhang

Found 11 papers, 7 papers with code

Focus on the Action: Learning to Highlight and Summarize Jointly for Email To-Do Items Summarization

no code implementations Findings (ACL) 2022 Kexun Zhang, Jiaao Chen, Diyi Yang

Automatic email to-do item generation is the task of generating to-do items from a given email to help people overview emails and schedule daily work.

DeFT: Flash Tree-attention with IO-Awareness for Efficient Tree-search-based LLM Inference

no code implementations30 Mar 2024 Jinwei Yao, Kaiqi Chen, Kexun Zhang, Jiaxuan You, Binhang Yuan, Zeke Wang, Tao Lin

Decoding using tree search can greatly enhance the inference quality for transformer-based Large Language Models (LLMs).

Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions

no code implementations28 Feb 2024 Kexun Zhang, Yee Man Choi, Zhenqiao Song, Taiqi He, William Yang Wang, Lei LI

On the contrary, we observe that 2000 endangered languages, though without a large corpus, have a grammar book or a dictionary.

Understanding the Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation

1 code implementation5 Feb 2024 Xinyi Wang, Alfonso Amayuelas, Kexun Zhang, Liangming Pan, Wenhu Chen, William Yang Wang

To understand how pre-training with a next-token prediction objective contributes to the emergence of such reasoning capability, we propose that we can view an LM as deriving new conclusions by aggregating indirect reasoning paths seen at pre-training time.

Knowledge Graphs Math

Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding

1 code implementation10 Oct 2023 Kexun Zhang, Hongqiao Chen, Lei LI, William Wang

Instruction-tuned large language models (LLMs) excel at many tasks but often fail to use external tools due to complicated and unfamiliar syntax constraints.

Math valid

Zero-Shot Detection of Machine-Generated Codes

1 code implementation8 Oct 2023 Xianjun Yang, Kexun Zhang, Haifeng Chen, Linda Petzold, William Yang Wang, Wei Cheng

We then modify the previous zero-shot text detection method, DetectGPT (Mitchell et al., 2023) by utilizing a surrogate white-box model to estimate the probability of the rightmost tokens, allowing us to identify code snippets generated by language models.

Language Modelling Text Detection

Invisible Image Watermarks Are Provably Removable Using Generative AI

1 code implementation2 Jun 2023 Xuandong Zhao, Kexun Zhang, Zihao Su, Saastha Vasan, Ilya Grishchenko, Christopher Kruegel, Giovanni Vigna, Yu-Xiang Wang, Lei LI

However, if we do not require the watermarked image to look the same as the original one, watermarks that keep the image semantically similar can be an alternative defense against our attack.

Image Denoising

Large Language Models Are Partially Primed in Pronoun Interpretation

1 code implementation26 May 2023 Suet-Ying Lam, Qingcheng Zeng, Kexun Zhang, Chenyu You, Rob Voigt

Recent psycholinguistic studies suggest that humans adapt their referential biases with recent exposure to referential patterns; closely replicating three relevant psycholinguistic experiments from Johnson & Arnold (2022) in an in-context learning (ICL) framework, we found that InstructGPT adapts its pronominal interpretations in response to the frequency of referential patterns in the local discourse, though in a limited fashion: adaptation was only observed relative to syntactic but not semantic biases.

In-Context Learning

ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers

1 code implementation NeurIPS 2023 Kexun Zhang, Danqing Wang, Jingtao Xia, William Yang Wang, Lei LI

To address these challenges, we propose ALGO, a framework that synthesizes Algorithmic programs with LLM-Generated Oracles to guide the generation and verify their correctness.

Code Generation

A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation

no code implementations NAACL 2022 Kexun Zhang, Rui Wang, Xu Tan, Junliang Guo, Yi Ren, Tao Qin, Tie-Yan Liu

Furthermore, we take the best of both and design a new loss function to better handle the complicated syntactic multi-modality in real-world datasets.

Machine Translation Translation

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