Papers by Qiming Zhang

12 papers
Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law (2025.acl-long)

Copied to clipboard

Challenge: Large language models have demonstrated impressive performance across a wide range of tasks, but this achievement comes with the trade-off of significant computational demands.
Approach: They propose a scaling law that decomposes the overall validation loss and assigns different importance weights to tokens to assess a specific meta-capability.
Outcome: The proposed model can predict the loss trending of models across different levels of computation without a gap between validation loss and model's downstream capabilities.
Orthogonal Subspace Learning for Language Model Continual Learning (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for continual learning in language models suffer catastrophic forgetting when learning sequential tasks.
Approach: They propose an orthogonal low-rank adaptation approach for continual learning in language models that uses orthogons to learn sequentially.
Outcome: The proposed approach outperforms state-of-the-art methods on continual learning benchmarks and preserves generalization ability of LLMs on unseen tasks.
FactVerse: A Benchmark for Factual Consistency in Interleaved Image–Text Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks lack effective mechanisms to evaluate factual consistency in interleaved image-text generation.
Approach: They propose a benchmark dedicated to evaluating factual consistency in interleaved image-text generation.
Outcome: The proposed framework outperforms existing evaluation methods in evaluating factual consistency in interleaved image-text generation.
Across Programming Language Silos: A Study on Cross-Lingual Retrieval-Augmented Code Generation (2026.findings-acl)

Copied to clipboard

Challenge: Current research on large language models with retrieval-augmented code generation (RACG) has focused on single-language settings, leaving their cross-lingual effectiveness underexplored.
Approach: They construct a dataset covering 13 PLs with nearly 14K instances to study cross-lingual code knowledge transfer in RACG.
Outcome: The proposed model shows unequal cross-lingual knowledge transfer even with direct injection and shows limited reliance on natural language information embedded in code when equipped with a code-specific retriever.
CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention (2025.acl-long)

Copied to clipboard

Challenge: Large Vision-Language Models (LVLMs) have impressive multimodal abilities but remain prone to multilingual object hallucination.
Approach: They propose a cross-lingual attention intervention method to mitigate multilingual object hallucination in LVLMs by aligning attention patterns.
Outcome: The proposed method improves 13.56% (up to 30%) on the POPE and 21.75% on the hallucination subsets across languages.
EmoCharacter: Evaluating the Emotional Fidelity of Role-Playing Agents in Dialogues (2025.naacl-long)

Copied to clipboard

Challenge: EmoCharacter evaluates emotional fidelity of role-playing agents in dialogues . current evaluations focus on personality fidelity, tone imitation, and knowledge consistency .
Approach: They propose a benchmark to assess emotional fidelity of role-playing agents in dialogues using large language models.
Outcome: The proposed benchmark measures emotional fidelity of role-playing agents and the characters they portray.
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to RLVR use multiple-choice questions as verifiable rewards . however, not all tasks provide reliable verification .
Approach: They propose a framework that actively constructs high-quality distractors to block elimination shortcuts and promote deep reasoning.
Outcome: The proposed method significantly improves reasoning capabilities of Large Language Models.
Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation (2026.acl-long)

Copied to clipboard

Challenge: a benchmark is designed to evaluate the capability of Large Multimodal Models (LMMs) in converting complex, structured digital graphics into executable code.
Approach: They propose a benchmark to evaluate the capability of Large Multimodal Models to convert digital graphics into executable code.
Outcome: The proposed benchmark exposes the performance gap among leading LMMs . the benchmark features 1130 meticulously curated samples .
Disco-RAG: Discourse-Aware Retrieval-Augmented Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing RAG strategies treat retrieved passages in a flat and unstructured way, which prevents the model from capturing structural cues and constrains its ability to synthesize knowledge from dispersed evidence across documents.
Approach: They propose a framework that explicitly injects discourse signals into the generation process.
Outcome: Experiments on question answering and long-document summarization benchmarks show the efficacy of the proposed framework.
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data (2024.findings-emnlp)

Copied to clipboard

Challenge: Reinforcement Learning from Human Feedback (RLHF) relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and pose challenges in sample efficiency and stability.
Approach: They propose an innovative framework that leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model’s responses.
Outcome: The proposed framework matches and exceeds the effectiveness of Proximal Policy Optimization (PPO) in terms of convergence speed and alignment of model responses with human preferences.
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for visually rich document understanding lack layout-centered knowledge . experimental results show that ERNIE-Layout improves layout awareness .
Approach: They propose a document pre-training solution with layout knowledge enhancement in the whole workflow to learn better representations that combine the features from text, layout, and image.
Outcome: The proposed model outperforms existing models on key downstream tasks.
Navigating the OverKill in Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Recent studies have highlighted a tendency among large language models to refuse to answer benign queries.
Approach: They propose a model-agnostic approach to reduce excessive attention to harmful words like ‘kill’ and a method to decode the next-token predictions by contrastive decoding.
Outcome: The proposed approach reduces the refusal rate by 20% while having little impact on safety.

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