Papers by Yizhe Huang

14 papers
Temporal Scaling Law for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies have found that the test loss of LLMs scales as power-laws with model size, computational budget, and dataset size.
Approach: They propose a concept of Temporal Scaling Law to study test loss of LLMs . they break down test loss into fine-grained token positions and develop a dynamic hyperbolic-law .
Outcome: The proposed model predicts the test loss of LLMs as the training steps scale up.
INSET: Sentence Infilling with INter-SEntential Transformer (2020.acl-main)

Copied to clipboard

Challenge: Missing sentence generation fosters a wide range of applications in natural language generation . Developing models for sentence infilling can potentially facilitate many text generation applications .
Approach: They propose a framework to decouple the problem from natural language processing . they propose generating missing sentences that can syntactically and semantically bridge context .
Outcome: The proposed model learns a sentence representation and generates 'missing sentences' the proposed model can be used for document auto-completion and meeting note expansion .
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.
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to formalizing mathematical statements face limitations in accuracy, especially in the context of complex, highlevel problems that involve sophisticated mathematical reasoning.
Approach: They propose a CriticLean framework that elevates the role of the critic from a passive validator to an active learning component and introduce a benchmark to measure models’ ability to distinguish semantically correct from incorrect formalizations.
Outcome: The proposed framework outperforms open- and closed-source benchmarks and shows that it significantly outperformed existing models.
Fast Quiet-STaR: Thinking Without Thought Tokens (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models have achieved impressive performance across a range of tasks, but further gains require more than scaling up model sizes or training data.
Approach: They propose a method that gradually reduces the number of thought tokens . this method allows models to internalize more abstract reasoning processes .
Outcome: The proposed framework preserves the benefits of token-level reasoning while reducing computational cost.
Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Recent studies show that Large language models struggle with handling long token sequences due to limited training context size.
Approach: They propose a single-stage continual pretraining method to equip LLMs with long context modeling capabilities.
Outcome: The proposed method outperforms existing methods on 4 language modeling benchmarks.
On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization (2024.findings-emnlp)

Copied to clipboard

Challenge: Reinforcement Learning from Human Feedback (RLHF) is an effective approach for aligning language models to human preferences.
Approach: They compare the accuracy of DPORM and EXRM with a reward function for scoring human preferences.
Outcome: The proposed methods can approximate an EXRM on the limit infinite samples, but it is unclear how effective they are in practice.
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.
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