arXiv subjects

Zhengze Zhang

Publications and source records attributed to Zhengze Zhang.

4 recordsLinked to original sources

arXiv2026

GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models

Citations provide the basis for trusting scientific claims; when they are invalid or fabricated, this trust collapses. With the advent of Large Language Models (LLMs), this risk has intensified: LLMs are increasingly used for academic writing, but their tendency to fabricate citations (``ghost citations'') poses a systemic threat to citation validity. To quantify this threat, we develop \citeb, an open-source framework for large-scale citation verification, and conduct a comprehensive study of citation validity in the LLM era through three complementary experiments. First, we benchmark 13 LLMs on citation generation task in various research domains, finding that all models hallucinate citations at rate from 14.23\% to 94.93\%. Second, we analyze 2.2 million citations from 56,381 papers at AI/ML and Security venues (2020--2025), finding that 1.07\% of papers contain invalid citations, with an 80.9\% increase in 2025. Third, we survey 97 researchers, finding that 87.2\% use AI-powered tools in their workflows, 76.7\% of reviewers do not thoroughly check references, and 74.5\% view peer review as ineffective at catching citation errors. Based on these findings, we argue that ghost citations represent a systemic threat to academic integrity, and call for coordinated efforts from community to address this challenge.

cs.CR↗

arXiv2025

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation

KV Cache is commonly used to accelerate LLM inference with long contexts, yet its high memory demand drives the need for cache compression. Existing compression methods, however, are largely heuristic and lack dynamic budget allocation. To address this limitation, we introduce a unified framework for cache compression by minimizing information loss in Transformer residual streams. Building on it, we analyze the layer attention output loss and derive a new metric to compare cache entries across heads, enabling layer-wise compression with dynamic head budgets. Additionally, by contrasting cross-layer information, we also achieve dynamic layer budgets. LAVa is the first unified strategy for cache eviction and dynamic budget allocation that, unlike prior methods, does not rely on training or the combination of multiple strategies. Experiments with benchmarks (LongBench, Needle-In-A-Haystack, Ruler, and InfiniteBench) demonstrate its superiority. Moreover, our experiments reveal a new insight: dynamic layer budgets are crucial for generation tasks (e.g., code completion), while dynamic head budgets play a key role in extraction tasks (e.g., extractive QA). As a fully dynamic compression method, LAVa consistently maintains top performance across task types. Our code is available at https://github.com/MGDDestiny/Lava.

cs.LG↗

arXiv2025

daDPO: Distribution-Aware DPO for Distilling Conversational Abilities

Large language models (LLMs) have demonstrated exceptional performance across various applications, but their conversational abilities decline sharply as model size decreases, presenting a barrier to their deployment in resource-constrained environments. Knowledge distillation with Direct Preference Optimization (dDPO) has emerged as a promising approach to enhancing the conversational abilities of smaller models using a larger teacher model. However, current methods primarily focus on 'black-box' KD, which only uses the teacher's responses, overlooking the output distribution offered by the teacher. This paper addresses this gap by introducing daDPO (Distribution-Aware DPO), a unified method for preference optimization and distribution-based distillation. We provide rigorous theoretical analysis and empirical validation, showing that daDPO outperforms existing methods in restoring performance for pruned models and enhancing smaller LLM models. Notably, in in-domain evaluation, our method enables a 20% pruned Vicuna1.5-7B to achieve near-teacher performance (-7.3% preference rate compared to that of dDPO's -31%), and allows Qwen2.5-1.5B to occasionally outperform its 7B teacher model (14.0% win rate).

cs.LG↗

arXiv2024

Reward Difference Optimization For Sample Reweighting In Offline RLHF

With the rapid advances in Large Language Models (LLMs), aligning LLMs with human preferences become increasingly important. Although Reinforcement Learning with Human Feedback (RLHF) proves effective, it is complicated and highly resource-intensive. As such, offline RLHF has been introduced as an alternative solution, which directly optimizes LLMs with ranking losses on a fixed preference dataset. Current offline RLHF only captures the "ordinal relationship" between responses, overlooking the crucial aspect of how much one is preferred over the others. To address this issue, we propose a simple yet effective solution called Reward Difference Optimization, shorted as RDO. Specifically, we introduce reward difference coefficients to reweigh sample pairs in offline RLHF. We then develop a difference model which captures rich interactions between a pair of responses for predicting these difference coefficients. Experiments with 7B LLMs on the HH and TL;DR datasets substantiate the effectiveness of our method in both automatic metrics and human evaluation, thereby highlighting its potential for aligning LLMs with human intent and values

cs.CL↗