Papers by Zhisong Zhang

26 papers
Agentic Knowledgeable Self-awareness (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have achieved considerable performance across various agentic planning tasks.
Approach: They propose a data-centric approach that applies agents with knowledgeable self-awareness like humans to a heuristic situation judgement criterion to mark special tokens on their self-explored trajectories for collecting training data.
Outcome: The proposed paradigm outperforms baseline models on various tasks with minimal external knowledge.
Recall with Reasoning: Chain-of-Thought Distillation for Mamba’s Long-Context Memory and Extrapolation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing long-context memory methods such as Mamba struggle with long-constituency when the length of the processed text exceeds the model's training length.
Approach: They propose a method that uses chain-of-thought summarization to teach Mamba to actively recall and reason over long contexts.
Outcome: Experiments on LONGMEMEVAL and HELMET show that RwR outperforms existing long-term memory methods while preserving short-context capabilities.
Transfer Learning from Semantic Role Labeling to Event Argument Extraction with Template-based Slot Querying (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods for event argument extraction are limited by the limited amount of annotations available.
Approach: They propose to use SRL annotations for event argument extraction . they propose to specify natural language-like queries to tackle label mismatch problem .
Outcome: The proposed model achieves impressive zero-shot results on English benchmarks . it also provides benefits in low-resource cases, where few annotations are available .
A Thorough Examination of Decoding Methods in the Era of LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Decoding methods are essential for converting language models from next-token predictors into practical task solvers.
Approach: They propose to evaluate decoding methods in general-purpose large language models . they find that decoding method performance is notably task-dependent .
Outcome: The proposed methods perform task-dependently and are influenced by alignment, model size, and quantization.
Reasons to Reject? Aligning Language Models with Judgments (2024.findings-acl)

Copied to clipboard

Challenge: a new framework for aligning large language models with judgments is proposed to help with alignment . a framework that allows for fine-grained inappropriate content detection and correction based on judgments . large language model alignment is critical for making artificial intelligence a reliable ally for humanity .
Approach: They propose a framework that allows for fine-grained inappropriate content detection and correction based on judgments.
Outcome: The proposed framework beats the 175B DaVinci003 and improves on AlpacaEval using judgments.
WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms (2026.eacl-short)

Copied to clipboard

Challenge: Recent studies have adopted a greedy one-way search strategy to deal with dynamic web environments.
Approach: They propose to integrate a rollback mechanism into web agents to allow them to revert back to a previous state in navigation trajectory.
Outcome: The proposed method is able to revert back to a previous state in its navigation trajectory, allowing the models to directly control the search process.
An Empirical Exploration of Local Ordering Pre-training for Structured Prediction (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have shown that pre-training contextualized encoders with language model objectives is effective for structured prediction.
Approach: They propose a semi-supervised method for pre-training contextualized encoders with language model objectives.
Outcome: The proposed method is effective on three typical structured prediction tasks in four languages.
Low-Bit Quantization Favors Undertrained LLMs (2025.acl-long)

Copied to clipboard

Challenge: Larger models or those trained on fewer tokens exhibit less quantization-induced degradation (QiD), while smaller, well-trained models face significant performance losses.
Approach: They propose to use QiD to measure an LLM’s training levels and determine the number of training tokens required for fully training LLMs of various sizes.
Outcome: The proposed scaling laws can predict the quantization performance of different-sized LLMs trained with tokens.
WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models (2026.acl-long)

Copied to clipboard

Challenge: Existing agentic systems are retrieval-heavy but reasoning-light . current systems lack compositional reasoning, a key component of deep research .
Approach: They propose a data synthesis pipeline WebAggregator to shift agentic paradigm . they use Proactive Explorer to collect interconnected knowledge and Compositional Logic Proposer to weave knowledge into complex questions .
Outcome: The proposed pipeline surpasses GPT-4.1 and matches Claude-3.7-Sonnet on GAIA, WebWalkerQA, and XBench.
On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling (2021.emnlp-main)

Copied to clipboard

Challenge: Recent advances in neural architectures and pre-trained representations have greatly improved the performance of fully-supervised semantic role labeling (SRL) but there are limitations in the availability of supervised training data.
Approach: They propose to leverage syntactic dependencies to facilitate cross-lingual transfer by annotating predicate-argument structures in text.
Outcome: The proposed model can be extended to other languages with limited training data.
Data-efficient Active Learning for Structured Prediction with Partial Annotation and Self-Training (2023.findings-emnlp)

Copied to clipboard

Challenge: Structured prediction is a fundamental problem in NLP, wherein the label space consists of complex structured outputs with groups of interdependent variables.
Approach: They propose a partial annotation approach that selects only the most informative sub-structures for annotation and a method that incorporates the current model's automatic predictions as pseudo-labels for un-annotated sub-structurals.
Outcome: The proposed approach reduces annotation cost over strong full annotation baselines under a fair comparison scheme that takes reading time into consideration.
An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing (P19-1)

Copied to clipboard

Challenge: In the past few years, graph-based dependency parsers have led to impressive empirical successes on parsing accuracy.
Approach: They propose to use a graph-based dependency parser to model global outputs.
Outcome: The proposed model has been shown to perform better on sentence-level Complete Match metric compared with the previous model.
UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing work lacks direct and fair evaluation of Large Language Models’ ability to express uncertainty effectively in long-form generation.
Approach: They propose a benchmark to evaluate uncertainty expression in both long- and short-form question answering (QA) they propose prompt-based and training-based methods to improve models’ performance.
Outcome: The proposed method mitigates this issue but a misalignment persists in uncertainty expression between long- and short-form generation.
LoGU: Long-form Generation with Uncertainty Expressions (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) generate factually incorrect content, i.e., hallucinations, despite impressive performance.
Approach: They propose a framework to enable models to express uncertainty when unsure . they propose atomic claims to refine uncertainty and refine it using supervised fine-tuning and direct preference optimization to enhance uncertainty expression.
Outcome: The proposed framework significantly improves accuracy, reduces hallucinations, and maintains comprehensiveness of responses.
Exploring Recombination for Efficient Decoding of Neural Machine Translation (D18-1)

Copied to clipboard

Challenge: Neural Machine Translation (NMT) decoder captures features of entire prediction history . some partial hypotheses with different prefixes will be regarded differently no matter how similar they are .
Approach: They propose a method that uses a n-gram suffix to adapt it to beam search decoding.
Outcome: The proposed method can obtain similar translation quality with a smaller beam size, making it more efficient.
Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections (P19-1)

Copied to clipboard

Challenge: Current systems for syntactic analysis tasks rely heavily on large scale annotated data.
Approach: They propose to learn a generative model with a structured prior that uses labeled source and unlabeled target data jointly.
Outcome: The proposed model improves on part-of-speech tagging and dependency parsing tasks on English as the only source corpus and on a wide range of target languages.
WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback (2025.findings-emnlp)

Copied to clipboard

Challenge: Web agents powered by Large Language Models lack the ability to perform in uncertain web environments.
Approach: They propose to reconstruct web agents' reasoning skills into chain-of-thought rationales by fine-tuning their LLM backbone into a web-based model.
Outcome: The proposed approach significantly improves the agent self-improving benchmark OpenWebVoyager, demonstrating that it can be used to improve the agent's reasoning skills.
WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model (2025.emnlp-main)

Copied to clipboard

Challenge: Agent self-improvement, where agents train their underlying Large Language Model (LLM) on self-sampled trajectories, shows promising results but often stagnates in web environments due to limited exploration and under-utilization of pretrained web knowledge.
Approach: They propose a co-evolving Large Language Model (LLM) that predicts the next observation based on current observation and action within the web environment.
Outcome: The proposed framework shows that agents can perform better in real-world web environments without using any distillation from more powerful close-sourced models.
Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large language models have demonstrated remarkable performance across a wide range of language tasks due to their remarkable ability in context modeling.
Approach: They propose to use parallel context encoding to reduce attention entropy by incorporating attention sinks and selective mechanisms to reduce irregular attention . they also propose to incorporate attention sink mechanisms into the parallel encoded context to reduce the irregular attention.
Outcome: The proposed methods lower irregular attention entropy and narrow performance gaps.
On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing (N19-1)

Copied to clipboard

Challenge: Existing studies on crosslingual transfer have focused on word-level information sharing, but words are not independent in sentences; their combinations form larger linguistic units, known as context.
Approach: They propose to use orderagnostic models to transfer word order to distant languages . they train dependency parsers on an English corpus and evaluate their transfer performance on 30 other languages.
Outcome: The proposed model performs better on languages with different word orders than on other languages.
A Two-Step Approach for Implicit Event Argument Detection (2020.acl-main)

Copied to clipboard

Challenge: et al., 2015) only consider local arguments in the same sentence of the event trigger.
Approach: They propose to decompose the implicit event argument detection task into two sub-problems . they propose to use argument head-word detection and head-to-span expansion to reduce the number of candidates.
Outcome: The proposed model achieves better performance than a strong sequence labeling baseline.
Towards More Efficient Insertion Transformer with Fractional Positional Encoding (2023.eacl-main)

Copied to clipboard

Challenge: Empirical studies on text generation tasks demonstrate the effectiveness of insertion-based models.
Approach: They propose a reusable positional encoding scheme for insertion transformers that allows reusing representations calculated in previous steps.
Outcome: Empirical studies show that the proposed model reduces the time required to generate a token and improves decoding efficiency.
A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression (2025.acl-long)

Copied to clipboard

Challenge: gist-based context compression methods can achieve only slight performance loss on tasks like retrieval-augmented generation and long-document QA, but it faces challenges in tasks like synthetic recall.
Approach: They propose two strategies to improve gist-based context compression in large language models.
Outcome: The proposed methods can achieve only slight performance loss on retrieval-augmented generation and long-document QA tasks, but they face challenges in tasks like synthetic recall.
Incorporating a Local Translation Mechanism into Non-autoregressive Translation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods to capture local dependencies among output tokens are not efficient, causing errors of repeated translation.
Approach: They propose a local autoregressive translation mechanism that predicts a short sequence of tokens for each target decoding position instead of one token.
Outcome: Empirical results show that the proposed method achieves comparable or better performance with fewer decoding iterations, bringing a 2.5x speedup.
A Survey of Active Learning for Natural Language Processing (2022.emnlp-main)

Copied to clipboard

Challenge: Existing literature surveys on active learning for NLP are too specific or too general, covering deep active learning.
Approach: They propose to use active learning to improve model learning and annotation cost for NLP problems.
Outcome: The proposed approach is based on a large dataset of data-driven machine learning models.
Choosing Transfer Languages for Cross-Lingual Learning (P19-1)

Copied to clipboard

Challenge: Cross-lingual transfer is a useful tool for improving performance of natural language processing (NLP) on low-resource languages.
Approach: They propose to use cross-lingual transfer to improve accuracy of low-resource languages . they build models that consider features to perform prediction on such languages based on ranking problem .
Outcome: The proposed model predicts good transfer languages much better than baselines considering single features in isolation.

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