Zifeng Wang
Zifeng Wang is a research scientist at Google, working on exciting machine learning algorithms and their applications. His research interests include efficient model adaptation, continual learning, and large language models. He received his PhD in machine learning from Northeastern University advised by Prof. Jennifer Dy.
Research Areas
Authored Publications
Sort By
Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
Zilong Wang
Steven Zheng
Swaroop Mishra
Yuwei Zhang
Anush Mattapalli
Ankur Taly
Jingbo Shang
ICLR 2025
Preview abstract
Retrieval augmented generation (RAG) has attracted a lot of attention across both academia and industry due to its capability in inserting timely and accurate evidence to the generation by large language models. However, the introduction of retrieved evidence largely makes the input prompt longer, which would harm the understanding quality of large language models and make it slower in actual usage scenarios. To solve these issues, we propose SpeculativeRAG, which leverages a smaller LLM to conduct the retrieval augmented generation for a larger LLM. The smaller LLM can digest a few pieces of evidence and generate multiple pieces of drafts in parallel rapidly, and these drafts will be verified by a large LLM to guarantee the quality. We achieve a higher speed as well as a better quality in the RAG results.
View details
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
Lei Li
Wenda Xu
Rishabh Agarwal
William Wang
Dhruv Madeka
ICLR 2025
Preview abstract
Recent knowledge distillation (KD) research made significant progress on improving smaller student models to match larger teachers' performances. Two noticeable methods, supervised KD and on-policy KD emerged as the state-of-the-art approaches. However, supervised KD for auto-regressive models suffers from distribution mismatch between training over fixed dataset and inference over student generated outputs. Conversely, on-policy KD, which uses student-generated samples for training, can suffer from low-quality training examples and the teacher's potential inaccuracies in assessing these samples. To address these limitations, we introduce Speculative Knowledge Distillation (SKD). Instead of solely training on teacher- or student-proposed samples, SKD leverages the student model to initially propose tokens following its own generation distribution. Subsequently, the teacher model is employed to replace tokens that are deemed out-of-distribution. Compared with supervised KD, the samples generated by SKD are more likely to align with the student's inference-time distribution, and 2) SKD can mitigate the generation of low-quality sequences by incorporating the teacher's feedback at each token. Furthermore, we demonstrate that SKD is a generic framework capable of implementing both supervised and on-policy knowledge distillation as specific instances. To validate SKD's effectiveness, we apply it to distill autoregressive large language models for various tasks, including translation, summarization, math, and instruction following. Our experiments consistently demonstrate SKD's superior performance compared to existing methods across different domains, tasks, data sizes, and model initialization strategies.
View details
HEART: Emotionally-driven test-time scaling of Language Models
Souradip Chakraborty
Gabriela Pinto
2025
Preview abstract
Test-time scaling has shown considerable success in improving the performance of language models on complex reasoning tasks without requiring fine-tuning. However, current strategies, such as self-reflection or ensembling, primarily focus on logical or structural refinement. They do not leverage the guiding potential of affective feedback. Inspired by psychological research showing that emotions can modulate cognitive performance, we introduce HEART--a novel framework that uses emotionally-driven prompts for iterative self-correction. HEART provides feedback on a models' incorrect response using a curated set of concise, emotionally charged phrases based on Paul Ekman's six basic emotions. By systematically varying the emotional tone of the feedback across iterations, our method guides the model to escape flawed reasoning paths and explore more promising alternatives. We evaluate our framework on challenging reasoning benchmarks including OlympiadBench, Humanity's Last Exam, and SimpleQA. Across these benchmarks, our approach delivers significantly deeper reasoning which leads to consistent and significant increase in accuracy compared to existing prompting methods. Crucially, these gains are observed across a diverse range of model architectures, demonstrating the broad applicability of our technique. Overall, our findings suggest that the next frontier in machine reasoning may lie not just in refining logic, but also in understanding and leveraging the 'HEART' of the models.
View details
Multi-turn Function-calling via Graph-based Execution and Translation
Kai-Wei Chang
Ke Jiang
Jindong Gu
Fan Yin
2025
Preview abstract
We propose a principled method to synthesize high-quality multi-turn function calling trajectories to align large language model (LLM)-based agents. We start with iteratively building function calling graph and defining node operations to increase its complexity. This enables us to construct reliable reference. Then, based on the synthesized function calling graph, we adopt back-and-forth translation to first construct multi-turn user queries and then, fill in the function arguments with information in the query. We sample positive trajectories that distill the function graph reference and negative trajectories that contrast with the positive trajectories in targeted loss patterns in multi-turn scenarios. Training with the positive trajectories with supervised fine-tuning and preference optimization against negative trajectories, we obtain 67.42 on BFCL and 71.7 on ToolQuery with an open-sourced model with 14B parameters, surpassing the performance of strong proprietary models like o1.
View details
PlanGEN: A Framework Utilizing Inference-Time Algorithms with LLM Agents for Planning and Reasoning
Hootan Nakhost
Mihir Parmar
Swaroop Mishra
Chitta Baral
Jindong Gu
2025
Preview abstract
Scaling inference-time computation in Large Language Models (LLMs) dramatically improves their capabilities for solving complex problems. While test-time scaling has shown promise in many tasks such as code generation and mathematical reasoning, integration of inference-time algorithms into multi-agent frameworks for planning and reasoning remains under-explored. To this end, we explore popular inference-time algorithms—Best of N, Tree of Thought (ToT), and REward BAlanced SEarch (REBASE)—with proposed feedback-driven refinement. Our feedback-driven refinement employs specialized agents: a constraint agent to enforce task instance-specific constraints, and a verifier agent to evaluate plan quality. Furthermore, we hypothesize that test-time scaling can be proportional to instance-level complexity. Thus, we propose an additional selection agent to dynamically optimize algorithm choice. We evaluate our proposed approaches on four different benchmarks, i.e., NATURAL PLAN, GPQA, OlympiadBench, and DocFinQA. Experimental results show that our methods outperform strong baselines, achieving state-of-the-art results in NATURAL PLAN, OlympiadBench , and DocFinQA. Our key findings demonstrate that constraint-guided iterative refinement and algorithm selection improves both planning and downstream reasoning in LLMs
View details
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
Wenda Xu
Dhruv Madeka
Lei Li
William Wang
Rishabh Agarwal
2025
Preview abstract
Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the knowledge gaps between teacher-student in practical scenarios. Supervised KD suffers from a distribution mismatch between training with a static dataset and inference over final student-generated outputs. Conversely, on-policy KD, which uses student-generated samples for training, can suffer from low-quality training examples with which teacher models are not familiar, resulting in inaccurate teacher feedback. To address these limitations, we introduce Speculative Knowledge Distillation (SKD), a novel approach that leverages cooperation between student and teacher models to generate high-quality training data on-the-fly while aligning with the student’s inference-time distribution. In SKD, the student proposes tokens, and the teacher replaces poorly ranked ones based on its own distribution, transferring high-quality knowledge adaptively. We evaluate SKD on various text generation tasks, including translation, summarization, math, and instruction following, and show that SKD consistently outperforms existing KD methods across different domains, data sizes, and model initialization strategies
View details
SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL
Satya Gundabathula
Hanjun Dai
Hootan Nakhost
TMLR (2024)
Preview abstract
Text-to-SQL, the process of translating natural language into Structured Query Language
(SQL), represents a transformative application of large language models (LLMs), potentially
revolutionizing how humans interact with data. This paper introduces the SQL-PaLM
framework, a comprehensive solution for understanding and enhancing Text-to-SQL using
LLMs, using in the learning regimes of few-shot prompting and instruction fine-tuning. With
few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error filtering. With instruction fine-tuning, we delve deep in understanding the critical
paradigms that influence the performance of tuned LLMs. In particular, we investigate
how performance can be improved through expanded training data coverage and diversity,
synthetic data augmentation, and integrating query-specific database content. We propose
a test-time selection method to further refine accuracy by integrating SQL outputs from
multiple paradigms with execution feedback as guidance. Additionally, we tackle the
practical challenge of navigating intricate databases with a significant number of tables and
columns, proposing efficient techniques for accurately selecting relevant database elements to
enhance Text-to-SQL performance. Our holistic approach yields substantial advancements
in Text-to-SQL, as demonstrated on two key public benchmarks, Spider and BIRD. Through
comprehensive ablations and error analyses, we shed light on the strengths and weaknesses
of our framework, offering valuable insights into Text-to-SQL’s future work.
View details
LMDX: Language Model-based Document Information Extraction And Localization
Kai Kang
Florian Luisier
Xiaoyu Sun
Ramya Sree Boppana
Zilong Wang
Jiaqi Mu
Hao Zhang
Nan Hua
Findings of the Association for Computational Linguistics ACL 2024, Association for Computational Linguistics, Bangkok, Thailand and virtual meeting, pp. 15140-15168
Preview abstract
Large Language Models (LLM) have revolutionized Natural Language Processing (NLP), improving state-of-the-art and exhibiting emergent capabilities across various tasks. However, their application in extracting information from visually rich documents, which is at the core of many document processing workflows and involving the extraction of key entities from semi-structured documents, has not yet been successful. The main obstacles to adopting LLMs for this task include the absence of layout encoding within LLMs, which is critical for high quality extraction, and the lack of a grounding mechanism to localize the predicted entities within the document. In this paper, we introduce Language Model-based Document Information EXtraction and Localization (LMDX), a methodology to reframe the document information extraction task for a LLM. LMDX enables extraction of singular, repeated, and hierarchical entities, both with and without training data, while providing grounding guarantees and localizing the entities within the document. Finally, we apply LMDX to the PaLM 2-S and Gemini Pro LLMs and evaluate it on VRDU and CORD benchmarks, setting a new state-of-the-art and showing how LMDX enables the creation of high quality, data-efficient parsers.
View details
Preview abstract
Grounded generation aims to equip language models (LMs) with the ability to produce more credible and accountable responses by accurately citing verifiable sources. However, existing methods, by either feeding LMs with raw or preprocessed materials, remain prone to errors. To address this, we introduce CaLM, a novel verification framework. CaLM leverages the insight that a robust grounded response should be consistent with information derived solely from its cited sources. Our framework empowers smaller LMs, which rely less on parametric memory and excel at processing relevant information given a query, to validate the output of larger LMs. Larger LM responses that closely align with the smaller LMs' output, which relies exclusively on cited documents, are verified. Responses showing discrepancies are iteratively refined through a feedback loop. Experiments on three open-domain question-answering datasets demonstrate significant performance gains of 1.5% to 7% absolute average without any required model fine-tuning.
View details
CodecLM: Aligning Language Models with Tailored Synthetic Data
Chun-Liang Li
Jin Miao
NAACL 2024
Preview abstract
Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token prediction objective and users' actual goals. To reduce the labor and time cost to collect or annotate data by humans, researchers start to explore the use of LLMs to generate instruction-aligned synthetic data. Recent works focus on generating diverse instructions and applying LLM to increase instruction complexity, often neglecting downstream use cases. It remains unclear how to tailor high-quality data to elicit better instruction-following abilities in different target instruction distributions and LLMs. To this end, we introduce CodecLM, a general framework for adaptively generating high-quality synthetic data for LLM alignment with different downstream instruction distributions and LLMs. Drawing on the Encode-Decode principles, we use LLMs as codecs to guide the data generation process. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution, and then decode metadata to create tailored instructions. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples. Extensive experiments on four open-domain instruction following benchmarks validate the effectiveness of CodecLM over the current state-of-the-arts.
View details
