Papers by Jiale Zhang

19 papers
One Cognitive Loop Is Enough: SODA unlocks Pure-Text Spatial Reasoning in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing large language models (LLMs) lack visual input, leading to errors in basic numerical comparisons.
Approach: They propose a spatial OODA framework that integrates the OODAC cognitive loop into multiple control tasks and integrates it into LLMs.
Outcome: The proposed model significantly improves the spatial reasoning capabilities of large language models across multiple scenarios including SPOD-Bench, SPACE and applications.
RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for generating open-ended rubrics suffer from scalability bottlenecks and coarse criteria resulting in a supervision ceiling effect.
Approach: They propose a framework for automated Coarse-to-Fine Rubric Generation . their framework uses principle-guided synthesis, multi-model aggregation, difficulty evolution .
Outcome: The proposed framework produces comprehensive and highly discriminative criteria capable of capturing the subtle nuances.
InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing safety detection systems have limitations in terms of their versatility and interpretability.
Approach: They introduce a safety detection framework that unifies 7 common sub-tasks into a uniform formulation and process 39 human-annotated datasets for instruction tuning.
Outcome: The proposed framework unifies 7 common sub-tasks into a uniform formulation and then runs on 39 human-annotated datasets to fine-tune it.
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated better safety performance in high-resource languages than in low-resourced languages.
Approach: They propose language-agnostic semantic alignment (LASA) which anchors safety alignment directly in semantic bottlenecks.
Outcome: The proposed approach significantly improves safety across all languages: average attack success rate drops from 24.7% to 2.8% on LLaMA-3.1-8B-Instruct and remains within 3–4% across Qwen2.5 and Qwend3 Instruct models (7B–32B).
AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment.
Approach: They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references.
Outcome: The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references.
A Survey of Post-Training Scaling in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated proficiency in understanding and generating human natural languages.
Approach: They propose a framework for scaling large language models using supervised fine-tuning, RLxF and test-time compute methodologies.
Outcome: The proposed model can be used to understand and generate human natural languages.
Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to detect toxic generation of pretrained language models rely on templates, data extraction, crowdsourcing workers or automatic generation.
Approach: They propose a method to construct adversarial contexts conditioned on a given response . they augment existing dataset BAD+ and construct a new dataset B AD+ .
Outcome: The proposed method can detect toxic or biased content in large pretrained language models.
Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs (2026.eacl-long)

Copied to clipboard

Challenge: Existing studies have shown that Vision-Language Models have robust multimodal reasoning capabilities, but their robustness against textual misinformation remains under-explored.
Approach: They propose to use visual-question-answering (VQA) prompts to generate persuasive prompts that deliberately conflict with visual evidence to test their models.
Outcome: The proposed framework shows that models are vulnerable to misleading prompts, and show an average performance drop of over 48.2% after only one round of persuasive conversation.
Training Language Model to Critique for Better Refinement (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have remarkable evaluation and critique capabilities, providing insightful feedback and identifying flaws in various tasks.
Approach: They propose a framework to train critic models using refinement signals to generate feedback loops where critiques guide the model in refining its responses.
Outcome: The proposed framework outperforms traditional methods and open-source models in terms of critique quality and refinement outcomes.
Glyph: Scaling Context Windows via Visual-Text Compression (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) traditionally represent text as sequences of discrete tokens . a long-context scaling problem requires processing more tokens more efficiently .
Approach: They propose a framework that renders long texts into compact visual pages and processes them with a vision-language model.
Outcome: The proposed framework renders long texts into compact visual pages and processes them with a vision-language model.
VideoQA-TA: Temporal-Aware Multi-Modal Video Question Answering (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for video question answering align visual or textual features directly with large language models, limiting the deep semantic association between modalities and hindering a comprehensive understanding of interactions within spatial and temporal contexts.
Approach: They propose a temporal-aware framework for multi-modal video question answering that aligns videos and questions at fine-grained levels.
Outcome: The proposed framework improves reasoning ability and accuracy of videoQA by aligning videos and questions at fine-grained levels.
Iterative Constrained Back-Translation for Unsupervised Domain Adaptation of Machine Translation (2022.coling-1)

Copied to clipboard

Challenge: Existing back-translation methods focus on in-domain lexical knowledge, which may lead to poor translation of unseen in- domain words.
Approach: They propose an iterative constrained back-translation method to incorporate in-domain lexical knowledge into synthetic parallel data from BT.
Outcome: The proposed method improves the BLEU score by up to 3.08 on four domains.
IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)

Copied to clipboard

Challenge: Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content.
Approach: They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question .
Outcome: The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types.
Exposing Privacy Risks in Graph Retrieval-Augmented Generation (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have limitations such as generating factually incorrect information (hallucinations) Retrieval-Augmented Generation (RAG) is a powerful paradigm for enhancing LLMs with external, up-to-date knowledge.
Approach: They investigate the data extraction vulnerabilities of Graph RAG systems by executing tailored attacks on them.
Outcome: The proposed attacks exploit the vulnerability of Graph RAG systems to leak raw text and structured data.
LongSafety: Evaluating Long-Context Safety of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating long sequences.
Approach: They propose a benchmark to evaluate LLM safety in open-ended long-context tasks . they find that relevant context and extended input sequences can exacerbate safety risks .
Outcome: The proposed benchmark identifies significant safety vulnerabilities in 16 LLMs . strong safety performance in short-context scenarios does not correlate with safety in long-contact tasks .
Divide, Optimize, Merge: Scalable Fine-Grained Generative Optimization for LLM Agents (2025.findings-emnlp)

Copied to clipboard

Challenge: LLM-based generative optimization has shown remarkable potential in improving agentic systems, but the current approach of prompting with the trajectories on the whole training dataset becomes untenable as datasets grow.
Approach: They propose a scalable framework that divides large optimization tasks into manageable subsets and performs targeted optimizations.
Outcome: The proposed framework outperforms conventional approach by 1.6-8.6% while reducing average prompt token consumption by 56.3%.
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement (2026.acl-long)

Copied to clipboard

Challenge: Existing multi-LLM collaboration systems often encounter scalability challenges when integrating new LLMs and tasks.
Approach: They propose a Scalable Multi-LLM Collaboration System to coordinate multiple open-source LLMs.
Outcome: The proposed system outperforms prevailing closed-source LLMs on eight mainstream benchmarks on multiple tasks.
Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing detection methods for large language models rely on fixed strategies to steal watermarks.
Approach: They propose a novel steal-based watermark algorithm that derives watermark information from watermarked texts to craft highly targeted adversarial attacks.
Outcome: The proposed system significantly increases steal efficiency against target watermarks under identical conditions.
AI2Agent: An End-to-End Framework for Deploying AI Projects as Autonomous Agents (2025.acl-demo)

Copied to clipboard

Challenge: a new framework automates deployment and debugging of AI projects . complexity of environment configurations, dependency conflicts, and debuggering issues hinder scalability and adoption.
Approach: They propose an end-to-end framework that automates AI project deployment . they conducted experiments on 30 AI deployment cases to evaluate its effectiveness .
Outcome: The proposed framework reduces deployment time and improves success rates by reducing human intervention.

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