Papers by Jinhao Duan

8 papers
IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation (2026.acl-long)

Copied to clipboard

Challenge: Recent approaches to quantify uncertainty in LLMs produce short or constrained answer sets, but many real-world applications require long-form and free-form text generation.
Approach: They propose a framework that leverages inter-sample consistency and intra-sampled faithfulness to quantify the uncertainty in long-form LLM outputs.
Outcome: The proposed framework provides reliable measures of claim-level uncertainty and the model’s faithfulness over two widely used long-form generation datasets.
Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) show promising results in language generation but often “hallucinate”, making their outputs less reliable.
Approach: They propose to shift attention to more relevant components at token- and sentence-levels for better UQ.
Outcome: The proposed approach improves the performance of a range of popular “off-the-shelf” LLMs with model sizes extending up to 33B parameters.
Dialogue is Better Than Monologue: Instructing Meidcal LLMs via Strategic Conversations (2026.findings-eacl)

Copied to clipboard

Challenge: Existing tuning methods for medical AI models are monologue-based . existing benchmarks are based on licensing exams or research articles .
Approach: They propose a benchmark to expose limitations of monologue-based tuning for medical AI models . they use a large dialogue dataset to capture stepwise diagnostic reasoning .
Outcome: The proposed model outperforms monologue-tuned models on a medical question answering task and improves accuracy on standard medical QA benchmarks.
ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees (2024.findings-emnlp)

Copied to clipboard

Challenge: Uncertainty quantification (UQ) in natural language generation tasks remains an open challenge . however, black-box uncertainty measures require investigating with the proliferation of LLMs served via APIs.
Approach: They propose a conformal uncertainty measure and a method to transform heuristic uncertainty notions into rigorous prediction sets.
Outcome: Empirical results show that the proposed method outperforms state-of-the-art methods and can provide reliable guarantees for open-ended NLG tasks.
ReTA: Recursively Thinking Ahead to Improve the Strategic Reasoning of Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Existing logical reasoning evaluations of Large Language Models (LLMs) focus on single-turn and static environments, such as arithmetic problems.
Approach: They propose a Recursively Thinking-Ahead agent that analyzes the opponents’ future moves/actions and assigns reward signals for these situations.
Outcome: The proposed agent is based on two scenarios: Online Racing and Offline Probing.
GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing (2025.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated their effectiveness in human-guided dialogues, but tasks in the real world are more complex and require greater autonomy from LLMs.
Approach: They propose to characterize LLM-guided conversation into three fundamental components: Goal Navigation, Context Management, Empathetic Engagement and implement an interviewing environment for the evaluation of LLMs.
Outcome: The proposed LLM outperforms baseline LLMs in interviewing quality and autobiography generation quality.
Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Ambiguity is pervasive in real-world questions, yet large language models often respond with confident answers rather than seeking clarification.
Approach: They show that question ambiguity is linearly encoded in the internal representations of large language models (LLMs) by training linear probes, they identify sparse sets of Ambiguity-Encoding Neurons (AENs)
Outcome: The proposed model outperforms prompting-based and representation-based baselines on ambiguity detection and generalization.
DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation (2025.findings-acl)

Copied to clipboard

Challenge: Existing code benchmarks for large language models remain static, resulting in data contamination and unreliable evaluation results.
Approach: They propose a dynamic, complexity-aware benchmark that overcomes the limitations of static datasets and provides a memorization-advantaged benchmark.
Outcome: DynaCode generates 189 million unique nested code problems across 4 units of code complexity and 16 types of call graphs.

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