Papers by Jianhao Zhang

19 papers
RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: The application scope of large language models (LLMs) is expanding . however, evaluating whether models can respond to user feedback has not been thoroughly analyzed.
Approach: They propose a benchmark to assess whether large language models can respond to refuting feedback and adhere to user demands throughout the conversation.
Outcome: The proposed benchmark covers tasks such as question answering, machine translation, and email writing.
Non-Autoregressive Document-Level Machine Translation (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing non-autoregressive translation models struggle with document context and handling discourse phenomena.
Approach: They propose a simple but effective design of sentence alignment between source and target to improve their performance on document-level machine translation.
Outcome: The proposed model achieves high acceleration on documents and sentence alignment significantly enhances their performance.
CAKE: Causal-Guided Adaptive Knowledge Editing for LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing knowledge editing methods rely on fixed-layer selection and uniform residual assignment, ignoring heterogeneous causal efficacy of different layers.
Approach: They propose a method that allows for a causally-guided adaptive knowledge editing that combines causal tracing scores with a constrained quadratic optimization problem.
Outcome: The proposed method achieves comparable performance with comparable overhead.
PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion (2022.findings-emnlp)

Copied to clipboard

Challenge: Pretrained language models (LMs) are a powerful transfer learning approach for knowledge graph (KG) completion.
Approach: They propose a parameter-lite transfer learning approach for pretrained language models for knowledge graph (KG) completion.
Outcome: The proposed model outperforms the state-of-the-art models on a knowledge graph completion benchmark by tuning 1% of the parameters.
TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Automated theorem proving (ATP) benchmarks focus on symbolic inference but rarely involve understanding complex number combination reasoning.
Approach: They propose a benchmark that requires a model to reduce a trigonometric expression with step-by-step proof and evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.
Outcome: The proposed benchmark evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.
Keys to Robust Edits: From Theoretical Insights to Practical Advances (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for modifying parametric memory are prone to inaccuracies due to conflicting or outdated information.
Approach: They propose a plug-and-play module that disentangles editing keys from native model representations and dynamically adjusts keys via contrastive learning to achieve robustness-specificity balance.
Outcome: The proposed method improves over robustness tests by up to 66.4% while maintaining the success rate unaffected.
DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for decoding target language are degenerate, hallucinating or empty.
Approach: They propose a method that tunes down the Softmax temperature to reduce autoregressive over-smoothness by label smoothing the output distributions.
Outcome: The proposed method improves MBR in various settings.
Generate & Rank: A Multi-task Framework for Math Word Problems (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing studies formalize MWP as a generation task but mathematical expressions are prone to minor mistakes.
Approach: They propose a ranking task for math word problem (MWP) that learns from its own mistakes and distinguishes between correct and incorrect expressions.
Outcome: The proposed model outperforms baselines on the classical Math23k dataset and is 7% higher than the state-of-the-art.
BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search (2026.findings-acl)

Copied to clipboard

Challenge: Existing RL-based agentic search models fail to recognize reasoning boundaries and rarely admit "I DON'T KNOW" lack of reliability leads to plausible but unreliable answers, introducing significant risks .
Approach: They propose a framework to cultivate reliable boundary awareness without compromising accuracy.
Outcome: Experiments show that the proposed framework improves the reliability of agentic search models.
AlphaEdit+: Model Editing in the Presence of Conflicting and Inconsistent Knowledge (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for knowledge editing struggle with knowledge conflicts and inconsistencies.
Approach: They propose a new method for knowledge editing that relaxes null-space constraints and introduces a weighting scheme to mitigate conflicts between new and historical knowledge.
Outcome: The proposed method outperforms existing methods on challenging datasets and outperformed existing methods.
Explicit Syntactic Guidance for Neural Text Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing text generation models follow the sequence-to-sequence paradigm . generative grammar suggests humans generate language by learning language grammar .
Approach: They propose a syntax-guided generation schema that searches the syntax tree in a top-down direction.
Outcome: The proposed method outperforms autoregressive baselines on paraphrase generation and machine translation.
What Have We Achieved on Non-autoregressive Translation? (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies have shown that non-autoregressive (NAT) methods underperform autoregressive methods (AT) however, their evaluation using BLEU has been shown to weakly correlate with human annotations.
Approach: They propose to evaluate four representative NAT methods using BLEU to narrow the performance gap between autoregressive and autoregressive translations.
Outcome: The proposed methods underperform NAT and autoregressive methods under more reliable evaluation metrics.
Empirical Prior for Text Autoencoders (2024.findings-emnlp)

Copied to clipboard

Challenge: Variational Autoencoders (VAE) are used to train generative models with latent variables.
Approach: They propose a transition from Variational Autoencoders (VAE) to text autoencodeurs (AE) which model a compact latent space and preserves the capability of the language model itself.
Outcome: The proposed method generates higher quality and more diverse text than the VAE-based Transformer baselines, and is more efficient than previous approaches.
Dynamics of Instruction Fine-Tuning for Chinese Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Instruction tuning is a burgeoning method to elicit the general intelligence of Large Language Models.
Approach: They investigate the effects of data quantity, model size, and data construction methods on instruction tuning for Chinese LLMs.
Outcome: The proposed model includes over 40,000 high-quality instruction instances covering ten underlying abilities.
Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing (2025.acl-long)

Copied to clipboard

Challenge: Dynamical systems theory provides a framework for understanding iterative processes and evolution over time.
Approach: They propose to apply this perspective to large language models which iteratively map input text to output text and re-express meaning with linguistic variation.
Outcome: The proposed model reveals that paraphrases re-express meaning with linguistic variation limiting linguistic diversity .
Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4 (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to solving mathematical problems fall into two broad categories: informal methods and formal methods.
Approach: They propose to use LLM natural-language reasoning to discover answers . they introduce Discover And Prove framework that rewrites Hard Mode statements into Easy Mode ones for existing ATP provers.
Outcome: The proposed framework can be used to prove hard mode statements on ATP benchmarks.
Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation (2023.acl-long)

Copied to clipboard

Challenge: Existing work on cross-lingual summarization (CLS) does not consider crosslingual sources for summarizing.
Approach: They propose a cross-lingual conversation summarization benchmark that explicitly considers source context.
Outcome: The proposed method surpasses baselines on ConvSumX and 3 widely-used manual annotations.
Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling (2025.acl-long)

Copied to clipboard

Challenge: Expressive zero-shot voice conversion (VC) aims to modify source timbre to match unseen speaker . existing zero- shot VC systems struggle to reproduce paralinguistic information in highly expressive speech .
Approach: They propose a framework for expressive zero-shot voice conversion that uses hybrid content encoding and memory-augmented context-aware timbre modeling.
Outcome: The proposed framework surpasses state-of-the-art VC systems in speech naturalness, speaker similarity, and speaker similarness.
Measuring Social Norms of Large Language Models (2024.findings-naacl)

Copied to clipboard

Challenge: Existing datasets that evaluate a general understanding of social science are inadequate to understand social norms.
Approach: They propose a multi-agent framework to improve large language models’ ability to understand social norms by comparing them to elementary students.
Outcome: The proposed framework improves large language models to be on par with humans.

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