Hardware prefetchers such as SPP rely on address-delta history and perform poorly on event-driven workloads, where event-type switches invalidate recent patterns. On an HFT order-book engine, SPP achieves only 8.0% L2 prefetch accuracy with 85.9% late prefetches; on B+Tree under uniform-random access, it degrades IPC by 6.7–8.1%. We present STP (Semantic-Triggered Prefetcher), which exposes event type through one non-privileged x86 hint instruction, SETHINT imm8, and combines two lightweight mechanisms: an Event Footprint Table (EFT) that replays high-frequency missed lines at type transitions, and a PC-Localized Working Set (PLWS) that gates next-line prefetching by per-PC miss rate with asymmetric feedback throttling. In gem5 on one HFT and four B+Tree settings, STP achieves up to 10 × higher L2 prefetch accuracy with 3–10 × fewer requests (up to 90% less bandwidth). On HFT, STP improves IPC by 36.1% over NoPF and by 5.4% over SPP (0.543 vs. 0.515). Under low locality, STP limits impact to − 2.0% or +0.8%, where SPP drops 6.7–8.1%. Hardware cost is 5.4 KB, reducible to ~3.1 KB.

Existing automatic prompt engineering methods are typically designed for discriminative tasks, where new task prompts are iteratively refined with limited feedback from a single metric reflecting a single aspect. However, these approaches are suboptimal for generative tasks, which require more nuanced guidance beyond a single numeric metric to improve the prompt and optimize multiple aspects of the generated text. To address these challenges, we propose a novel multi-aspect Critique-Suggestion-guided automatic Prompt Optimization (CriSPO) approach. CriSPO introduces a critique-suggestion module as its core component. This module spontaneously discovers aspects, and compares generated and reference texts across these aspects, providing specific suggestions for prompt modification. These clear critiques and actionable suggestions guide a receptive optimizer module to make more substantial changes, exploring a broader and more effective search space. To further improve CriSPO with multi-metric optimization, we introduce an Automatic Suffix Tuning (AST) extension to enhance the performance of task prompts across multiple metrics. We evaluate CriSPO on 4 state-of-the-art Large Language Models (LLMs) across 4 summarization and 5 Question Answering (QA) datasets. Extensive experiments show 3-4% ROUGE score improvement on summarization and substantial improvement of various metrics on QA.

Mahnaz Koupaee, Jake W. Vincent, Saab Mansour, Igor Shalyminov, Han He, Hwanjun Song, Raphael Shu, Jianfeng He, Yi Nian, Amy Wing-mei Wong, Kyu J. Han, Hang Su. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

DataFlow has been emerging as a new paradigm for building task-oriented chatbots due to its expressive semantic representations of the dialogue tasks. Despite the availability of a large dataset SMCalFlow and a simplified syntax, the development and evaluation of DataFlow-based chatbots remain challenging due to the system complexity and the lack of downstream toolchains. In this demonstration, we present DFEE, an interactive DataFlow Execution and Evaluation toolkit that supports execution, visualization and benchmarking of semantic parsers given dialogue input and backend database. We demonstrate the system via a complex dialog task: event scheduling that involves temporal reasoning. It also supports diagnosing the parsing results via a friendly interface that allows developers to examine dynamic DataFlow and the corresponding execution results. To illustrate how to benchmark SoTA models, we propose a novel benchmark that covers more sophisticated event scheduling scenarios and a new metric on task success evaluation. The codes of DFEE have been released on https://github.com/amazonscience/dataflow-evaluation-toolkit.

Abstract Sequence-to-Sequence (S2S) models have achieved remarkable success on various text generation tasks. However, learning complex structures with S2S models remains challenging as external neural modules and additional lexicons are often supplemented to predict non-textual outputs. We present a systematic study of S2S modeling using contained decoding on four core tasks: part-of-speech tagging, named entity recognition, constituency, and dependency parsing, to develop efficient exploitation methods costing zero extra parameters. In particular, 3 lexically diverse linearization schemas and corresponding constrained decoding methods are designed and evaluated. Experiments show that although more lexicalized schemas yield longer output sequences that require heavier training, their sequences being closer to natural language makes them easier to learn. Moreover, S2S models using our constrained decoding outperform other S2S approaches using external resources. Our best models perform better than or comparably to the state-of-the-art for all 4 tasks, lighting a promise for S2S models to generate non-sequential structures.

Multi-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency while a question still remains whether or not it would perform as well on tasks that are distinct in nature.We first present MTL results on five NLP tasks, POS, NER, DEP, CON, and SRL, and depict its deficiency over single-task learning.We then conduct an extensive pruning analysis to show that a certain set of attention heads get claimed by most tasks during MTL, who interfere with one another to fine-tune those heads for their own objectives.Based on this finding, we propose the Stem Cell Hypothesis to reveal the existence of attention heads naturally talented for many tasks that cannot be jointly trained to create adequate embeddings for all of those tasks.Finally, we design novel parameter-free probes to justify our hypothesis and demonstrate how attention heads are transformed across the five tasks during MTL through label analysis.

This paper proposes a new framework of lossless data hiding (LDH) in JPEG images. The proposed framework contains two algorithms, i.e., the optimized basic LDH and the relay transfer based extension. In the basic algorithm, we aim to preserve the filesize after data embedding. The data hiding process is optimized by variable-length-code (VLC) mapping, combination and permutation. In the extended algorithm, we focus on embedding more bits into the bitstream with a condition that the filesize increment is allowed. To decrease the filesize increment, we propose a relay transfer based algorithm to preprocess the JPEG bitstream. Subsequently, we embed data into the processed bitstream using the basic LDH. Both algorithms provide better performances than previous arts. After lossless data hiding, the marked JPEG bitstream is compliant to common JPEG decoders. Since all operations are implemented on VLCs and the Huffman codes, no distortion is generated on the image pixels. Experimental results demonstrate that the proposed approach outperforms previous methods.