Dun Zhang
Author directory2026
Jasper-Flash: Elastic Token Compression and Progressive Distillation for Inference-Scalable Text Embedding Models
Haining An | Xingbing Chen | Wenbo Lyu | Dun Zhang | Ziyang Zeng | Zhenxiang Zhao | Rui Song | Hao Xu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Haining An | Xingbing Chen | Wenbo Lyu | Dun Zhang | Ziyang Zeng | Zhenxiang Zhao | Rui Song | Hao Xu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Deploying text embedding models under resource constraints is challenged by the sequence-length-dependent computational cost of self-attention. However, existing sequence-reduction strategies remain predominantly static and offer limited flexibility across inference budgets. We propose Jasper-Flash, an inference-scalable text embedding framework combining Elastic Token Compression (ETC) with Compression-Adaptive Progressive Distillation (CAPD). ETC uses a length threshold and a user-selected compression ratio to adjust sequence length on the fly, enabling flexible latency–quality trade-offs within a single model. To mitigate the optimization difficulty introduced by lossy sequence reduction, CAPD integrates heterogeneous multi-teacher distillation with a progressive curriculum over fixed and dynamically sampled compression ratios. We instantiate Jasper-Flash as Jasper-Token-Compression-600M, a bilingual text embedding model. Experiments on MTEB and C-MTEB demonstrate competitive performance across compression ratios and substantial reductions in encoding latency, particularly for longer inputs. The code and model are available at https://huggingface.co/infgrad/Jasper-Token-Compression-600M.
An Empirical Study of Position Bias in Visualized Text Retrieval
Cuiqiaoshu Pan | Ziyang Zeng | Dun Zhang | Yuqing Yang
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Cuiqiaoshu Pan | Ziyang Zeng | Dun Zhang | Yuqing Yang
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Visualized text retrieval, which renders text into images and retrieves them with vision-language models, has been proposed to avoid lossy text parsing and compress long contexts. We ask whether it also bypasses a known flaw of text retrieval: position bias, the tendency to overweight a passage’s beginning. Rendering 1D text into a 2D image may change the bias in two respects: its shape, which position is favored, and its magnitude, how strongly performance varies across positions. We test this by rendering the PosIR benchmark as controlled plain text images and comparing eight visual retrievers with four text retrievers on identical instances. We find that (1) position bias persists, with all visual retrievers exhibiting measurable bias (macro PSI 0.061–0.168); (2) its shape is transformed: seven of eight visual retrievers favor the middle of the page in an inverted-U pattern, contrasting with both the primacy bias of text retrievers and the lost-in-the-middle effect of LLMs with long contexts; (3) its magnitude is sensitive to rendering settings, as taller images amplify PSI and can even reverse positional preference, while font size has a similarly large effect; and (4) under matched backbones, visual retrievers exhibit lower position bias than their text counterparts on longer documents, but this advantage vanishes beyond the pixel budget and at document scale. Visualized text retrieval therefore does not eliminate position bias; it transforms a familiar 1D textual bias into a more complex 2D spatial bias.
2025
An Empirical Study of Position Bias in Modern Information Retrieval
Ziyang Zeng | Dun Zhang | Jiacheng Li | Zoupanxiang | Yudong Zhou | Yuqing Yang
Findings of the Association for Computational Linguistics: EMNLP 2025
Ziyang Zeng | Dun Zhang | Jiacheng Li | Zoupanxiang | Yudong Zhou | Yuqing Yang
Findings of the Association for Computational Linguistics: EMNLP 2025
This study investigates the position bias in information retrieval, where models tend to overemphasize content at the beginning of passages while neglecting semantically relevant information that appears later. To analyze the extent and impact of position bias, we introduce a new evaluation framework consisting of two position-aware retrieval benchmarks (SQuAD-PosQ, FineWeb-PosQ) and an intuitive diagnostic metric, the Position Sensitivity Index (PSI), for quantifying position bias from a worst-case perspective. We conduct a comprehensive evaluation across the full retrieval pipeline, including BM25, dense embedding models, ColBERT-style late-interaction models, and full-interaction reranker models. Our experiments show that when relevant information appears later in the passage, dense embedding models and ColBERT-style models suffer significant performance degradation (an average drop of 15.6%). In contrast, BM25 and reranker models demonstrate greater robustness to such positional variation. These findings provide practical insights into model sensitivity to the position of relevant information and offer guidance for building more position-robust retrieval systems. Code and data are publicly available at: https://github.com/NovaSearch-Team/position-bias-in-IR.
Search