Papers by Yizhe Yang

12 papers
Graph vs. Sequence: An Empirical Study on Knowledge Forms for Knowledge-Grounded Dialogue (2023.emnlp-main)

Copied to clipboard

Challenge: Knowledge-grounded dialogue systems can generate informative responses based on dialogue history and external knowledge source.
Approach: They conduct a thorough experiment to determine the optimal knowledge form, mutual effects between knowl- edge and model selection, and the few-shot performance of knowledge.
Outcome: The proposed method combines knowledge-grounded dialogue with human-generated dialogues to generate informative and meaningful responses.
Consistent Client Simulation for Motivational Interviewing-based Counseling (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to simulate human clients in mental health counseling are limited and cost prohibitive.
Approach: They propose a framework that supports consistent client simulation for mental health counseling by tracking the mental state of a simulated client, controlling its state transitions, and generating for each state behaviors consistent with the client’s motivation, beliefs, preferred plan to change, and and receptivity.
Outcome: The proposed framework can simulate human clients for mental health counseling tasks and achieve higher consistency than previous methods.
MIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing Counseling (2026.findings-acl)

Copied to clipboard

Challenge: Existing reasoning large language models (LLMs) generate responses without explicitly aligning thoughts with counseling techniques, limiting their effectiveness.
Approach: They propose a lightweight thinking model that generates therapeutic thoughts to guide MI counseling agents in strategy selection and response generation.
Outcome: The proposed model achieves theory-of-mind assessment comparable to state-of the-art systems with an order of magnitude less computation.
Speaker Verification in Agent-generated Conversations (2024.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have increased the capabilities of conversational AI to solve challenging dialogue problems.
Approach: They propose a task to verify whether two sets of utterances originate from the same speaker.
Outcome: The proposed task aims to verify whether two sets of utterances originate from the same speaker.
Fundamental Capabilities of Large Language Models and their Applications in Domain Scenarios: A Survey (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmark-based evaluations cannot accurately reflect the performance of real-world applications.
Approach: They propose a reliable strategy for domains to choose more robust LLMs for real-world applications.
Outcome: The proposed strategy addresses the challenges faced by domains to choose more robust LLMs for real-world applications.
ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues? (2025.emnlp-industry)

Copied to clipboard

Challenge: ECom-Bench is a benchmark framework for evaluating LLM agent with multimodal capabilities in e-commerce customer support domain.
Approach: They introduce a benchmark framework for evaluating LLM agent with multimodal capabilities in the e-commerce customer support domain.
Outcome: The proposed benchmark features dynamic user simulation based on persona information from real e-commerce customer interactions and a realistic task dataset derived from authentic ecommerce dialogues.
PUPPET: Neural-Symbolic Standardized Patients for Mental Health (2026.acl-long)

Copied to clipboard

Challenge: Existing LLM-based training approaches lack faithful responses to clinical errors and explainable feedback.
Approach: They propose a neural-symbolic virtual standardized patient governed by an OBSERVE-THINK-BEHAVE architecture that embeds LLM reasoning into a symbolic system where experts implant causal associations between intervention logic and patient mental states.
Outcome: The proposed model outperforms baselines in faithfulness and pedagogical value.
PSST: A Benchmark for Evaluation-driven Text Public-Speaking Style Transfer (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to transfer text style focus on sentence-level data, limiting performance . current LLMs struggle to generate public speaking texts that align with human preferences .
Approach: They propose a task to transform official texts into public-speaking styles by analyzing real-world data.
Outcome: The proposed task aims to transform public speaking texts into public-speaking styles . the proposed framework analyzes characteristics and identifies problems of stylized texts .
CAMI: A Counselor Agent Supporting Motivational Interviewing through State Inference and Topic Exploration (2025.acl-long)

Copied to clipboard

Challenge: Motivational Interviewing (MI) is a client-centered counseling technique designed to address ambivalence and facilitate behavior change in clients.
Approach: They propose to use a STAR framework to evoke change talk by using large language models to assess MI skill competency, client’s state inference accuracy, topic exploration proficiency, and overall counseling success.
Outcome: The proposed agent outperforms several state-of-the-art methods and shows more realistic counselor-like behavior.
Improving Text Generation with Student-Forcing Optimal Transport (2020.emnlp-main)

Copied to clipboard

Challenge: Maximum likelihood estimation (MLE) is used to train models, but during testing, the model is conditioned on previously generated tokens, resulting in exposure bias.
Approach: They propose to use optimal transport to match the sequences generated in MLE and test modes to reduce exposure bias.
Outcome: The proposed method is validated on machine translation, text summarization, and text generation tasks.
Unveiling and Addressing Pseudo Forgetting in Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing efforts to mitigate catastrophic forgetting in continual learning have not been studied.
Approach: They propose a rationale-guided replay framework that allows models to leverage their capabilities and provide partial external correct rationales to the original instructions.
Outcome: The proposed framework mitigates pseudo forgetting while maintaining model plasticity.
EvoWiki: Evaluating LLMs on Evolving Knowledge (2025.acl-long)

Copied to clipboard

Challenge: Existing knowledge evolution benchmarks are static and fail to capture the evolving nature of LLMs and knowledge.
Approach: They propose an evolving dataset that categorizes information into stable, evolved, and uncharted states.
Outcome: The proposed dataset is auto-updatable and enables evaluation of continuously changing knowledge and newly released LLMs.

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