Papers by Weihong Zhong

13 papers
Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage.
Approach: They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Outcome: The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models (2024.acl-long)

Copied to clipboard

Challenge: Large Vision-Language Models (LVLMs) suffer from multimodal hallucinations . however, the generated hallucines could influence the models’ subsequent generation .
Approach: They propose a framework to evaluate LVLMs' behaviors when encountering generated hallucinations and a method to revise the output distribution of LVLs with the one derived from the residual visual input.
Outcome: The proposed framework reduces the performance of open-source LVLMs by 31%, indicating that they are prone to accept the generated hallucinations and make false claims that they would not have supported without distractions.
Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression (2026.acl-long)

Copied to clipboard

Challenge: Recent methods to reduce the KV cache size fail to identify crucial KVs for generation while excluding others accurately, resulting in severe information loss.
Approach: They propose an intention-aware KV cache eviction method that identifies and retains crucial KVs according to the attention distribution of intention, which semantically reflects the user’s goal and determines which part of the context is relevant.
Outcome: The proposed method can maintain the model performance while reducing the KV cache size from 128K to 2K, leading to a 6.3x increase in decoding speed and 7.8x enhancement in memory efficiency compared to the default setting.
Video Question Answering: Datasets, Algorithms and Challenges (2022.emnlp-main)

Copied to clipboard

Challenge: Recent advances in video question answering have led to a surge in popularity . despite the popularity, VideoQA remains one of the greatest challenges .
Approach: They categorize the video question-answer datasets into normal VideoQA, multi-modal VideoQA and knowledge-based VideoQA according to the modalities invoked in the question-announcement pairs.
Outcome: The proposed methods are mainly designed for Factoid QA and inference VideoQA . the proposed methods have been compared with other methods and are robust and interpretable.
Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to enhance length extrapolation of large language models have been developed, but a systematic survey is lacking.
Approach: They propose to examine the effects of positional encoding on length extrapolation.
Outcome: The proposed methods improve the extrapolation of large language models, but they are still lacking a systematic survey.
Length Controlled Generation for Black-box LLMs (2025.acl-long)

Copied to clipboard

Challenge: Existing length control methods involve fine-tuning the parameters of LLMs, which is inefficient and suboptimal for practical use.
Approach: They propose an iterative sampling framework that regulates LLMs to generate length-constrained text without modifying the underlying parameters.
Outcome: The proposed method achieves 100% success rates on Llama3.1 tasks with minimal additional computational overhead.
Controllable Text Generation via Probability Density Estimation in the Latent Space (2023.acl-long)

Copied to clipboard

Challenge: Existing control approaches cannot effectively model complex space with diverse attributes, high dimensionality, and asymmetric structure, leaving subsequent controls unsatisfactory.
Approach: They propose a control framework using probability density estimation in the latent space and an invertible transformation function that maps the complex distributions to simple Gaussian distributions in the prior space.
Outcome: The proposed method outperforms baselines on attribute relevance and text quality, achieving a new SOTA.
Advancing Large Language Model Attribution through Self-Improving (2024.emnlp-main)

Copied to clipboard

Challenge: Teaching large language models to generate text with citations to evidence sources requires high-quality attribution data, which is costly and labor-intensive.
Approach: They propose a framework for iteratively improving the attribution capability of large language models (LLMs) by attributing output to verifiable sources.
Outcome: Experiments on three open-domain question-answering datasets show that START improves in aggregating information across multiple sources.
Extending Context Window of Large Language Models from a Distributional Perspective (2024.emnlp-main)

Copied to clipboard

Challenge: Existing scaling methods for extending context window rely on empirical approaches and lack understanding of the internal distribution within RoPE resulting in suboptimal performance.
Approach: They propose to optimize the context window extending task from the view of rotary angle distribution by minimizing disturbance between rotary angles to maintain consistency with the pre-training phase.
Outcome: The proposed approach reduces by up to 72% of the distributional disturbance when extending LLaMA2’s context window to 8k, and reduces it by up 32% when extending to 16k.
Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis (2025.coling-main)

Copied to clipboard

Challenge: Existing studies have focused on instance-level unlearning, specifically removing predefined instances containing sensitive content.
Approach: They propose a task to erase entity-related knowledge from the target model completely by analyzing the forget set and its size.
Outcome: The proposed task systematically evaluates popular unlearning algorithms and reveals that the knowledge coverage of the forget set and its size play pivotal roles.
Learning Fine-Grained Grounded Citations for Attributed Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: despite impressive performance, large language models still struggle with hallucinations . current approaches suffer from suboptimal citation quality due to reliance on in-context learning .
Approach: They propose a framework that teaches large language models to generate fine-grained citations.
Outcome: The proposed framework outperforms all baselines on the ALCE benchmark and achieves an average improvement of 14.21% in citation quality.
Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization (2025.acl-long)

Copied to clipboard

Challenge: Existing frameworks for retrieval-augmented large language models (LLMs) are lacking in LFQA faithfulness testing.
Approach: They propose a framework to teach retrieval-augmented large language models to explicitly discriminate between faithful and unfaithful generations.
Outcome: The proposed framework outperforms GPT-4o in LFQA scenarios and outperformed existing benchmarks.
MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing GUI benchmarks lack fine-grained diagnostics to identify which capabilities lead to task failures.
Approach: They propose a multilingual P R GUI Benchmark to assess LVLMs' language capabilities . they propose XLI to align non-English hidden states with English ones during inference .
Outcome: The proposed benchmark reveals consistent gaps between English and non-English settings . it reduces the cross-lingual gaps with an average gain of 6.5% in non- English settings compared to static benchmarks .

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