Papers by Nicholas Lee

7 papers
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement (2024.findings-acl)

Copied to clipboard

Challenge: Pretrained large language models are currently state-of-the-art for solving most tasks . however, many of them are in the low-data regime, making fine-tuning challenging . a new data augmentation strategy uses a teacher LLM to augment a small seed dataset .
Approach: They propose a targeted and iterative data augmentation strategy that augments a teacher LLM to fine-tune a small seed dataset by adding additional data.
Outcome: The proposed approach outperforms fine-tuning and other data augmentation strategies on a small seed dataset.
Evolutionary Strategies at Scale lead to Catastrophic Forgetting (2026.acl-short)

Copied to clipboard

Challenge: ES has been shown to improve performance on specific tasks, but it is accompanied by significant forgetting of prior abilities.
Approach: They propose to use Evolutionary Strategies to train gradient-free algorithms to improve performance.
Outcome: The proposed algorithm achieves performance numbers closer to GRPO for math and reasoning tasks, but forgets prior abilities.
RExBench: Can coding agents autonomously implement AI research extensions? (2026.acl-long)

Copied to clipboard

Challenge: Existing large language model (LLM) agents are not capable of performing research extension tasks autonomously.
Approach: They propose a benchmark to evaluate LLM agents' ability to extend existing AI research . they use extensions of 12 recently published research papers accompanied by domain expert-written instructions .
Outcome: The proposed benchmark evaluates 12 LLM agents implemented using aider and OpenHands.
TexPrax: A Messaging Application for Ethical, Real-time Data Collection and Annotation (2022.aacl-demo)

Copied to clipboard

Challenge: TexPrax is a messaging system to collect and annotate task-oriented dialog data . informal communication channels such as instant messengers are increasingly being used at work .
Approach: They propose a messaging system that collects and annotates task-oriented dialog data from employees via chatbots.
Outcome: The proposed system collects and annotates tasks-oriented dialog data from german factory workers and provides lightweight annotations.
TinyAgent: Function Calling at the Edge (2024.emnlp-demo)

Copied to clipboard

Challenge: Recent large language models (LLMs) have enabled the development of advanced agentic systems that can integrate various tools and APIs to fulfill user queries.
Approach: They propose an end-to-end framework for training and deploying task-specific small language model agents capable of function calling for driving agentic systems at the edge.
Outcome: The proposed model outperforms existing models by reducing the input prompt length and quantizing the inference speed.
Long Short-Term Memory as a Dynamically Computed Element-wise Weighted Sum (P18-2)

Copied to clipboard

Challenge: LSTMs were introduced to combat vanishing gradients in simple RNNs by augmenting them with gated additive recurrent connections.
Approach: They propose to decouple the LSTM’s gates from the embedded RNN and create a new class of RNNs where the recurrence computes an element-wise weighted sum of context-independent functions of the input.
Outcome: The proposed model performs as well as an LSTM on a range of problems, strongly suggesting that the gates are doing much more in practice than just alleviating vanishing gradients.
Deduplicating Training Data Makes Language Models Better (2022.acl-long)

Copied to clipboard

Challenge: Existing language modeling datasets contain near-duplicate examples and long repetitive substrings.
Approach: They develop tools that allow us to deduplicate existing language modeling datasets . they found that over 1% of the unprompted output of language models is copied verbatim .
Outcome: The proposed tools reduce train-test overlap, which affects over 4% of validation sets, and improve model accuracy.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations