Papers by Hongzhi Li

18 papers
Pay Attention to Implicit Attribute Values: A Multi-modal Generative Framework for AVE Task (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to extract attribute values from product descriptions are incomplete and noisy due to the tedious nature of this task.
Approach: They propose a framework to extract attributes from product descriptions to acquire implicit attributes in addition to the explicit ones.
Outcome: The proposed framework outperforms existing methods on the extraction of implicit attribute values while achieving comparable performance for the explicit ones.
Generalizable Cross-Lingual Cognitive Distortion Detection with Standardized Annotations and Multi-Task Learning (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on cognitive distortion have limited generalizability and performance of models in large-scale and cross-linguistic contexts.
Approach: They propose a multi-task learning model based on teacher student architecture solution which improves generalization performance.
Outcome: The proposed model improves generalizability and interpretability of the proposed model.
IterAlign: Iterative Constitutional Alignment of Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Empirical results show that iterAlign improves truthfulness, helpfulness, harmlessness and honesty, improving the LLM alignment by up to 13.5% in harmlessness.
Approach: They propose a data-driven constitution discovery and self-alignment framework called IterAlign to overcome these drawbacks by leveraging red teaming to uncover weaknesses of an LLM.
Outcome: Empirical results show that iterAlign improves truthfulness, helpfulness, harmlessness and honesty by up to 13.5%.
DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are evolving towards autonomous agents . retrieval capabilities are well-benchmarked, but post-retrieval synthesis is under-evaluated due to open-ended writing.
Approach: They propose a benchmark to evaluate information consolidation capabilities using survey papers as gold standards.
Outcome: The proposed benchmark analyzes the post-retrieval synthesis stage of large language models . it leverages high-quality survey papers as gold standards and reverse-engineers research requests . the proposed benchmark outperforms single-turn generation and reduces hallucinations .
Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems (2022.findings-acl)

Copied to clipboard

Challenge: Existing models memorize procedures from context and rely on shallow heuristics to solve MWPs.
Approach: They propose a contrastive learning approach where the neural network perceives the divergence of patterns.
Outcome: The proposed method greatly improves performance in monolingual and multilingual settings.
Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data (2026.acl-long)

Copied to clipboard

Challenge: Existing studies on robustness to explicit noise (e.g., document semantics) but overlook implicit noise (spurious features).
Approach: They propose a framework to quantify the robustness of RAGs against spurious features by integrating a data synthesis pipeline and a taxonomy.
Outcome: The proposed framework quantifies the robustness of RALMs against spurious features.
MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media (2025.emnlp-main)

Copied to clipboard

Challenge: Social media is a key platform for emotional expression, yet deep learning lacks flexibility and interpretability.
Approach: They propose to use Chinese social media to train interpretable mental health instruction datasets to test models' ability to explain their decisions.
Outcome: The proposed models outperform deep learning and LLMs on three mental health downstream tasks and demonstrate their potential for clinical applications.
PATS: Sensitivity-aware Noisy Learning for Pretrained Language Models (2022.emnlp-main)

Copied to clipboard

Challenge: A wide range of NLP tasks benefit from fine-tuning of pretrained language models (PLMs), however, a number of redundant parameters which contribute less to the downstream task are observed in a directly fine- tuned model.
Approach: They propose a noisy training mechanism which considers each parameter’s importance in the downstream task to help fine-tune pretrained language models.
Outcome: The proposed method can be used to fine-tune pretrained language models on a wide range of tasks and consistently achieve higher performance.
Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) fine-tuned using rejection sampling retain only correct reasoning trajectories . however, this paradigm treats supervision as a binary filter that systematically excludes teacher-generated errors, leaving a gap in how reasoning failures are modeled during training.
Approach: They propose a fine-tuning strategy that reframes rejection sampling as a structured supervision construction process.
Outcome: The proposed approach outperforms RFT on multiple math benchmarks while retaining only correct reasoning trajectories.
Large-Scale Relation Learning for Question Answering over Knowledge Bases with Pre-trained Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Existing KBQA methods focus on the natural language but ignore textual information carried by the nodes and edges.
Approach: They propose to perform relation extraction, relation matching, and relation reasoning tasks to align the natural language expressions to the relations in the KB and reason over the missing connections.
Outcome: Experiments on WebQSP show that the proposed model outperforms baselines even when the KB is incomplete.
Are Large Language Models (LLMs) Good Social Predictors? (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing studies suggest that Large Language Models can generate human-like responses, but it is unclear how well they work and where the plausible predictions derive from.
Approach: They propose to use LLMs to generate human-like responses by mutability and accessibility of social inputs to perform a social prediction task.
Outcome: The proposed model performs well in three realistic settings and a novel social prediction task.
CARE-CR: Context-Aware Routing and Expert Fusion for Multi-Preference Cognitive Restructuring (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) offer promising avenues for automated cognitive restructuring in mental health settings, but current approaches lack the adaptability to balance conflicting therapeutic dimensions, such as empathy and rationality.
Approach: They propose a decoupled optimization framework that implements a dimension-guided Monte Carlo tree search to train expert policies specialized for distinct therapeutic attributes rather than relying on a monolithic alignment strategy.
Outcome: The proposed framework achieves consistent improvements over baselines across multiple evaluation dimensions, including diagnostic accuracy, contextual appropriateness, task effectiveness, and overall helpfulness, while enabling controllable cognitive restructuring generation.
Chain-of-Specificity: Enhancing Task-Specific Constraint Adherence in Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Existing approaches to enhancing large language models fail to emphasize specific constraints and unlock the underlying knowledge.
Approach: They propose a method that emphasizes specific constraints and unlocks knowledge within LLMs by iteratively emphasising on specific constraints.
Outcome: The proposed method outperforms existing methods in enhancing generated content, especially in terms of specificity.
Let Me Check the Examples: Enhancing Demonstration Learning via Explicit Imitation (2023.acl-short)

Copied to clipboard

Challenge: Existing work only concatenates answered examples as demonstrations to prompt template without any additional operation, neglecting the prompt-demonstration dependencies.
Approach: They propose to concatenate answered examples as demonstrations to prompt template without any additional operation, neglecting the prompt-demonstration dependencies.
Outcome: Experiments show that the proposed method achieves state-of-the-art performance on 5 out of 14 classification corpus.
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing story generation benchmarks focus mainly on plot quality and fluency, leaving consistency errors unexplored.
Approach: They propose a benchmark to evaluate narrative consistency in long-form story generation.
Outcome: Evaluating LLMs, we find consistency errors are common in factual and temporal dimensions . authors say the findings can inform future efforts to improve consistency in long-form narrative generation.
AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications (2022.coling-1)

Copied to clipboard

Challenge: Existing methods to correct handwritten assignments are to use OCR to recognize characters and compare them to answers.
Approach: They propose a multimodal approach to correct handwritten Chinese characters by combining the visual information of students' handwriting with the encoded representations of answers.
Outcome: The proposed model outperforms OCR-based methods by a large margin.
Chinese MentalBERT: Domain-Adaptive Pre-training on Social Media for Chinese Mental Health Text Analysis (2024.findings-acl)

Copied to clipboard

Challenge: Existing models for language analysis are inadequate for specialized domains like psychology.
Approach: They have enriched a Chinese social media database with psychological lexicons to enhance its applicability to psychological text analysis.
Outcome: The proposed model performed better on six public datasets and provided relevant predictions given the masked sentences.
Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies on hallucination detection rely heavily on closed-source LLMs such as GPT-4.
Approach: They propose an LLM-based agent framework called HaluAgent that integrates LLMs, multi-functional toolbox and a memory mechanism for hallucination detection.
Outcome: The proposed framework integrates the LLM, multi-functional toolbox, and can detect hallucinations on Chinese and English datasets.

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