Papers by Eric Davis

6 papers
KoBEST: Korean Balanced Evaluation of Significant Tasks (2022.coling-1)

Copied to clipboard

Challenge: a well-formulated benchmark allows objective and precise evaluation of diverse models.
Approach: They propose a benchmark for Korean balanced evaluation of significant tasks that requires advanced Korean linguistic knowledge.
Outcome: The proposed benchmarks are based on five Korean-language downstream tasks . the data is annotated by humans and thoroughly reviewed to guarantee high data quality.
What, When, and How to Ground: Designing User Persona-Aware Conversational Agents for Engaging Dialogue (2023.acl-industry)

Copied to clipboard

Challenge: a personalized dialogue system can generate user-customized responses based on long-term memory about the user's persona.
Approach: They propose a method for building a personalized open-domain dialogue system . they combine weighted dataset blending and negative persona information augmentation methods .
Outcome: The proposed method balances dialogue fluency and tendency to ground while introducing a response-type label to improve controllability and explainability of the grounded responses.
TelBench: A Benchmark for Evaluating Telco-Specific Large Language Models (2024.emnlp-industry)

Copied to clipboard

Challenge: a growing demand for Large Language Models (LLMs) is requiring specialized models to augment customer service agents' skills.
Approach: They propose a methodology for developing a specialized Telecommunications LLM . they use a dataset to evaluate customer service expertise in the telecommunications domain .
Outcome: The proposed model improves the efficiency of customer service agents and reduces response times.
TelAgentBench: A Multi-faceted Benchmark for Evaluating LLM-based Agents in Telecommunications (2025.emnlp-industry)

Copied to clipboard

Challenge: Large Language Models (LLMs) are becoming powerful agentic systems . generic benchmarks fail to assess realistic, non-English performance .
Approach: They propose to evaluate five core agentic capabilities: Reasoning, Planning, Action (tool-use), Retrieval-Augmented Generation, and Instruction Following.
Outcome: The evaluations reveal significant performance disparities between models that employ explicit reasoning and those that do not.
The Indigenous Languages Technology project at NRC Canada: An empowerment-oriented approach to developing language software (2020.coling-main)

Copied to clipboard

Challenge: This paper describes the first, three-year phase of a project at the National Research Council of Canada that is developing software to assist Indigenous communities in preserving their languages and extending their use.
Approach: They describe the first phase of a project at the National Research Council of Canada that is developing software to assist Indigenous communities in preserving their languages.
Outcome: The proposed software will help Indigenous communities preserve and revitalize their languages and extend their use.
Adaptively profiling models with task elicitation (2025.emnlp-main)

Copied to clipboard

Challenge: Language model evaluations fail to characterize consequential failure modes, forcing experts to inspect outputs and build new benchmarks.
Approach: They propose a method that automatically builds new evaluations to profile model behavior.
Outcome: The proposed method finds that language models fail in hundreds of tasks . it also finds that o3-mini is prone to hallucination when fabrications are repeated .

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