PaperMetrixEvidence-aware discovery
EN
Interface language English EN العربية AR Türkçe TR
Create account
Researcher profile

Lyle Ungar

6 papers in the PaperMetrix corpus

Publications

Papers by this author

  1. Generalized SHAP: Generating multiple types of explanations in machine learning

    2020 · arXiv (Cornell University)

    Many important questions about a model cannot be answered just by explaining how much each feature contributes to its output. To answer a broader set of questions, we generalize a popular, mathematically well-grounded explanation technique, …

  2. Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments

    2020

    Although prediction of dialects is an important language processing task, with a wide range of applications, existing work is largely limited to coarse-grained varieties. Inspired by geolocation research, we propose the novel task of Micro-Dialect …

  3. Conceptor-Aided Debiasing of Large Language Models

    2023

    Pre-trained large language models (LLMs) reflect the inherent social biases of their training corpus. Many methods have been proposed to mitigate this issue, but they often fail to debias or they sacrifice model accuracy. We …

  4. Efficient RL for optimizing conversation level outcomes with an LLM-based tutor

    2025 · arXiv (Cornell University)

    Large language models (LLMs) built on existing reinforcement learning with human feedback (RLHF) frameworks typically optimize responses based on immediate turn-level human preferences. However, this approach falls short in multi-turn dialogue settings, such as online …

  5. Beyond the Strongest LLM: Multi-Turn Multi-Agent Orchestration vs. Single LLMs on Benchmarks

    2025 · arXiv (Cornell University)

    We study multi-turn multi-agent orchestration, where multiple large language model (LLM) agents interact over multiple turns by iteratively proposing answers or casting votes until reaching consensus. Using four LLMs (Gemini 2.5 Pro, GPT-5, Grok 4, …

  6. Unsupervised Post-Processing of Word Vectors via Conceptor Negation

    2019 · Proceedings of the AAAI Conference on Artificial Intelligence

    Word vectors are at the core of many natural language processing tasks. Recently, there has been interest in post-processing word vectors to enrich their semantic information. In this paper, we introduce a novel word vector …