Papers by Zhuohang Li

7 papers
From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have remarkable capabilities, but unreliability remains a barrier to deployment in high-stakes domains.
Approach: They propose to transform uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.
Outcome: The proposed model evolution from passive diagnostic metric to active control signal is critical for high-stakes applications.
SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for hallucination detection rely on self-consistency check alone . prominent LMs exhibit a tendency to produce exceedingly confident, but erroneous, assertions .
Approach: They propose a sampling-based method that expands on the principle of self-consistency checking to detect hallucinations at question-level and model-level.
Outcome: The proposed method outperforms the state of the art in detecting non-factual and factual statements across multiple question-answering and open-domain generation benchmarks.
Heuristic-based Search Algorithm in Automatic Instruction-focused Prompt Optimization: A Survey (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have led to remarkable achievements across a variety of NLP tasks.
Approach: They propose a taxonomy of automatic prompt optimization methods that explore and improve prompts with minimal human oversight.
Outcome: The proposed methods can explore and improve prompts with minimal human oversight.
Towards Statistical Factuality Guarantee for Large Vision-Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Advancements in Large Vision-Language Models (LVLMs) have demonstrated impressive performance in image-conditioned text generation, but hallucinated outputs pose a major barrier to their use in safety-critical applications.
Approach: They propose a conformal-prediction-based framework that achieves finite-sample distribution-free statistical guarantees to the factuality of LVLM output.
Outcome: The proposed framework reduces the error rate of LLaVa-1.5 claims from 87.8% to 10.0% while ensuring that the output is accurate.
SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches separate the optimization of prompt instructions and in-context learning examples, leading to incohesive, suboptimal results.
Approach: They propose a framework that refines both prompt instructions and in-context learning examples.
Outcome: The proposed framework outperforms state-of-the-art prompt optimization methods on 35 benchmark tasks.
Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Language models suffer from poor interpretability and transparency, as well as the intrinsic risk of hallucination and misinformation.
Approach: They propose a statistical framework that assesses how well a query can be answered by an RAG system by capturing the relevance of knowledge.
Outcome: The proposed framework assesses how well a query can be answered by an RAG system by capturing the relevance of knowledge.
Divide-Conquer-Reasoning for Consistency Evaluation and Automatic Improvement of Large Language Models (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing methods for evaluating the quality and consistency of text generated by Large Language Models are not effective.
Approach: They propose a divide-conquer-reasoning approach to evaluate LLM-generated texts using a split-and-conquers evaluator and an automatic metric converter to facilitate this approach.
Outcome: The proposed framework outperforms state-of-the-art methods by a large margin on multiple benchmarks and reduces 90% of output inconsistencies in one iteration.

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