AIConfPaper
← Search

Ahmed Hassan Awadallah

33 accepted papers

2026

Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning

Vaishnavi Shrivastava, Ahmed Hassan Awadallah, Vidhisha Balachandran, Shivam Garg, Harkirat Behl, Dimitris Papailiopoulos
ICLR 2026poster

Large language models trained with reinforcement learning on verifiable rewards often inflate response length—trading brevity for accuracy. While longer reasoning can help on hard problems, many extra tokens are filler: verbose text making little progress. We introduce GFPO (Group Filtered Policy Op…

Cited by 0Source ↗code ↗Scholar ↗
2025

Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF

Tengyang Xie, Dylan J Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Hassan Awadallah, Alexander Rakhlin
ICLR 2025poster

This paper investigates a basic question in reinforcement learning from human feedback (RLHF) from a theoretical perspective: how to efficiently explore in an online manner under preference feedback and general function approximation. We take the initial step towards a theoretical understanding of t…

Cited by 37Source ↗PDF ↗Scholar ↗
2025

Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents

Vardaan Pahuja, Yadong Lu, Corby Rosset, Boyu Gou, Arindam Mitra, Spencer Whitehead +2
ACL 2025finding

Recent success in large multimodal models (LMMs) has sparked promising applications of agents capable of autonomously completing complex web tasks. While open-source LMM agents have made significant advances in offline evaluation benchmarks, their performance still falls substantially short of human…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings

Yehya Farhat, Hamza ElMokhtar Shili, Fangshuo Liao, Chen Dun, Mirian Del Carmen Hipolito Garcia, Guoqing Zheng +4
NeurIPS 2025poster

Mixture-of-Experts (MoEs) achieve scalability by dynamically activating subsets of their components. Yet, understanding how expertise emerges through joint training of gating mechanisms and experts remains incomplete, especially in scenarios without clear task partitions. Motivated by inference cost…

Cited by 0Source ↗Scholar ↗
2025

Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation

Chen Dun, Mirian Del Carmen Hipolito Garcia, Guoqing Zheng, Ahmed Hassan Awadallah, Robert Sim, Anastasios Kyrillidis
AAAI 2025technical

Prompt instruction tuning is a popular approach to better adjust pretrained LLMs for specific downstream tasks. How to extend this approach to simultaneously handle multiple tasks and data distributions is an interesting question. We propose Mixture of Prompts (MoPs) with smart gating functionality.…

Cited by 5Source ↗PDF ↗Scholar ↗
2024

Assessing and Verifying Task Utility in LLM-Powered Applications

Negar Arabzadeh, Siqing Huo, Nikhil Mehta, Qingyun Wu, Chi Wang, Ahmed Hassan Awadallah +2
EMNLP 2024main

The rapid development of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents, assisting humans in their daily tasks. However, a significant gap remains in assessing to what extent LLM-powered applications genuinely enhance user experien…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2024

Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing

Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Rühle +2
ICLR 2024poster

Large language models (LLMs) excel in most NLP tasks but also require expensive cloud servers for deployment due to their size, while smaller models that can be deployed on lower cost (e.g., edge) devices, tend to lag behind in terms of response quality. Therefore in this work we propose a hybrid in…

Cited by 80Source ↗PDF ↗code ↗Scholar ↗
2024

Teaching Language Models to Hallucinate Less with Synthetic Tasks

Erik Jones, Hamid Palangi, Clarisse Simões Ribeiro, Varun Chandrasekaran, Subhabrata Mukherjee, Arindam Mitra +2
ICLR 2024poster

Large language models (LLMs) frequently hallucinate on abstractive summarization tasks such as document-based question-answering, meeting summarization, and clinical report generation, even though all necessary information is included in context. However, optimizing to make LLMs hallucinate less is…

Cited by 31Source ↗PDF ↗Scholar ↗
2023

AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation

Ganesh Jawahar, Subhabrata Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks Lakshmanan. V.S. +3
ACL 2023findings

Mixture-of-Expert (MoE) models have obtained state-of-the-art performance in Neural Machine Translation (NMT) tasks. Existing works in MoE mostly consider a homogeneous design where the same number of experts of the same size are placed uniformly throughout the network. Furthermore, existing MoE wor…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2023

Axiomatic Preference Modeling for Longform Question Answering

Corby Rosset, Guoqing Zheng, Victor Dibia, Ahmed Hassan Awadallah, Paul N. Bennett
EMNLP 2023long main

The remarkable abilities of large language models (LLMs) like ChatGPT and GPT-4 partially stem from the post-training processes involving human preferences encoded within a reward model as part of a Reinforcement Learning from Human Feedback (RLHF) regimen. These reward models (RMs) often lack dire…

Cited by 0Source ↗Scholar ↗
2023

DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models

Xuxi Chen, Tianlong Chen, Weizhu Chen, Ahmed Hassan Awadallah, Zhangyang Wang, Yu Cheng
ACL 2023long

Gigantic pre-trained models have become central to natural language processing (NLP), serving as the starting point for fine-tuning towards a range of downstream tasks. However, two pain points persist for this paradigm: (a) as the pre-trained models grow bigger (e.g., 175B parameters for GPT-3), ev…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2023

Logical Transformers: Infusing Logical Structures into Pre-Trained Language Models

Borui Wang, Qiuyuan Huang, Budhaditya Deb, Aaron Halfaker, Liqun Shao, Daniel McDuff +3
ACL 2023findings

Natural language contains rich logical structures and logical information, and correctly detecting and accurately understanding these logical structures and information underlying natural language texts is very crucial for NLP models’ performance on many important NLU and NLG tasks. Existing pre-tra…

Cited by 1Source ↗PDF ↗Scholar ↗
2023

On Improving Summarization Factual Consistency from Natural Language Feedback

Yixin Liu, Budhaditya Deb, Milagro Teruel, Aaron Halfaker, Dragomir Radev, Ahmed Hassan Awadallah
ACL 2023long

Despite the recent progress in language generation models, their outputs may not always meet user expectations. In this work, we study whether informational feedback in natural language can be leveraged to improve generation quality and user preference alignment. To this end, we consider factual con…

Cited by 42Source ↗PDF ↗code ↗Scholar ↗
2022

AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning

Yaqing Wang, Sahaj Agarwal, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah +1
EMNLP 2022main

Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models. To address this,…

Cited by 145Source ↗PDF ↗code ↗Scholar ↗
2022

Boosting Natural Language Generation from Instructions with Meta-Learning

Budhaditya Deb, Ahmed Hassan Awadallah, Guoqing Zheng
EMNLP 2022main

Recent work has shown that language models (LMs) trained with multi-task instructional learning (MTIL) can solve diverse NLP tasks in zero- and few-shot settings with improved performance compared to prompt tuning. MTIL illustrates that LMs can extract and use information about the task from instruc…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗
2022

Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models

Dongkuan Xu, Subhabrata Mukherjee, Xiaodong Liu, Debadeepta Dey, Wenhui Wang, Xiang Zhang +2
NeurIPS 2022accept

Traditional knowledge distillation (KD) methods manually design student architectures to compress large models given pre-specified computational cost. This requires several trials to find viable students, and repeating the process with change in computational budget. We use Neural Architecture Searc…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗
2022

Knowledge Infused Decoding

Ruibo Liu, Guoqing Zheng, Shashank Gupta, Radhika Gaonkar, Chongyang Gao, Soroush Vosoughi +2
ICLR 2022poster

Pre-trained language models (LMs) have been shown to memorize a substantial amount of knowledge from the pre-training corpora; however, they are still limited in recalling factually correct knowledge given a certain context. Hence. they tend to suffer from counterfactual or hallucinatory generation…

Cited by 29Source ↗PDF ↗code ↗Scholar ↗
2022

Leveraging Locality in Abstractive Text Summarization

Yixin Liu, Ansong Ni, Linyong Nan, Budhaditya Deb, Chenguang Zhu, Ahmed Hassan Awadallah +1
EMNLP 2022main

Neural attention models have achieved significant improvements on many natural language processing tasks. However, the quadratic memory complexity of the self-attention module with respect to the input length hinders their applications in long text summarization. Instead of designing more efficient…

Cited by 32Source ↗PDF ↗code ↗Scholar ↗
2021

A Conditional Generative Matching Model for Multi-lingual Reply Suggestion

Budhaditya Deb, Guoqing Zheng, Milad Shokouhi, Ahmed Hassan Awadallah
EMNLP 2021finding

We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously. Multilingual models are often challenged by model capacity and severe data distribution skew across languages. While prior works largely focus on monolingual models, we propose Conditio…

Cited by 2Source ↗PDF ↗Scholar ↗
2021

A Dataset and Baselines for Multilingual Reply Suggestion

Mozhi Zhang, Wei Wang, Budhaditya Deb, Guoqing Zheng, Milad Shokouhi, Ahmed Hassan Awadallah
ACL 2021long

Reply suggestion models help users process emails and chats faster. Previous work only studies English reply suggestion. Instead, we present MRS, a multilingual reply suggestion dataset with ten languages. MRS can be used to compare two families of models: 1) retrieval models that select the reply f…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2021

Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models

Boxin Wang, Chejian Xu, Shuohang Wang, Zhe Gan, Yu Cheng, Jianfeng Gao +2
NeurIPS 2021poster

Large-scale pre-trained language models have achieved tremendous success across a wide range of natural language understanding (NLU) tasks, even surpassing human performance. However, recent studies reveal that the robustness of these models can be challenged by carefully crafted textual adversarial…

Cited by 245Source ↗code ↗Scholar ↗
2021

An Exploratory Study on Long Dialogue Summarization: What Works and What’s Next

Yusen Zhang, Ansong Ni, Tao Yu, Rui Zhang, Chenguang Zhu, Budhaditya Deb +3
EMNLP 2021finding

Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series. However, real-world dialogues pose a great challenge to current summarization models, as the dialogue length typically exceeds the input limits imposed by recent transform…

Cited by 60Source ↗PDF ↗code ↗Scholar ↗
2021

Fairness via Representation Neutralization

Mengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Hassan Awadallah, Xia Hu
NeurIPS 2021poster

Existing bias mitigation methods for DNN models primarily work on learning debiased encoders. This process not only requires a lot of instance-level annotations for sensitive attributes, it also does not guarantee that all fairness sensitive information has been removed from the encoder. To address…

Cited by 95Source ↗PDF ↗Scholar ↗
2021

Few-Shot Learning Evaluation in Natural Language Understanding

Subhabrata Mukherjee, Xiaodong Liu, Guoqing Zheng, Saghar Hosseini, Hao Cheng, Greg Yang +3
NeurIPS 2021poster

Most recent progress in natural language understanding (NLU) has been driven, in part, by benchmarks such as GLUE, SuperGLUE, SQuAD, etc. In fact, many NLU models have now matched or exceeded "human-level" performance on many tasks in these benchmarks. Most of these benchmarks, however, give models…

Cited by 3Source ↗code ↗Scholar ↗
2021

MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning

Mengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Hassan Awadallah
NAACL 2021long

The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-resource languages. However, for extremely low-resource languages without large-scale monolingual corpora for pre-training…

Cited by 37Source ↗PDF ↗code ↗Scholar ↗
2021

NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction

Ahmed Elgohary, Christopher Meek, Matthew Richardson, Adam Fourney, Gonzalo Ramos, Ahmed Hassan Awadallah
NAACL 2021long

We study semantic parsing in an interactive setting in which users correct errors with natural language feedback. We present NL-EDIT, a model for interpreting natural language feedback in the interaction context to generate a sequence of edits that can be applied to the initial parse to correct its…

Cited by 49Source ↗PDF ↗Scholar ↗
2021

QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization

Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha +5
NAACL 2021long

Meetings are a key component of human collaboration. As increasing numbers of meetings are recorded and transcribed, meeting summaries have become essential to remind those who may or may not have attended the meetings about the key decisions made and the tasks to be completed. However, it is hard t…

Cited by 341Source ↗PDF ↗code ↗Scholar ↗
2021

SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing

Tao Yu, Rui Zhang, Alex Polozov, Christopher Meek, Ahmed Hassan Awadallah
ICLR 2021poster

Conversational Semantic Parsing (CSP) is the task of converting a sequence of natural language queries to formal language (e.g., SQL, SPARQL) that can be executed against a structured ontology (e.g. databases, knowledge bases). To accomplish this task, a CSP system needs to model the rel…

Cited by 79Source ↗PDF ↗Scholar ↗
2021

Say ‘YES’ to Positivity: Detecting Toxic Language in Workplace Communications

Meghana Moorthy Bhat, Saghar Hosseini, Ahmed Hassan Awadallah, Paul Bennett, Weisheng Li
EMNLP 2021finding

Workplace communication (e.g. email, chat, etc.) is a central part of enterprise productivity. Healthy conversations are crucial for creating an inclusive environment and maintaining harmony in an organization. Toxic communications at the workplace can negatively impact overall job satisfaction and…

Cited by 26Source ↗PDF ↗Scholar ↗
2021

Self-Training with Weak Supervision

Giannis Karamanolakis, Subhabrata Mukherjee, Guoqing Zheng, Ahmed Hassan Awadallah
NAACL 2021long

State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be useful in such settings to automatically generate weakly labeled training data…

Cited by 102Source ↗PDF ↗code ↗Scholar ↗
2021

Structure-Grounded Pretraining for Text-to-SQL

Xiang Deng, Ahmed Hassan Awadallah, Christopher Meek, Oleksandr Polozov, Huan Sun, Matthew Richardson
NAACL 2021long

Learning to capture text-table alignment is essential for tasks like text-to-SQL. A model needs to correctly recognize natural language references to columns and values and to ground them in the given database schema. In this paper, we present a novel weakly supervised Structure-Grounded pretraining…

Cited by 172Source ↗PDF ↗code ↗Scholar ↗
2021

SummerTime: Text Summarization Toolkit for Non-experts

Ansong Ni, Zhangir Azerbayev, Mutethia Mutuma, Troy Feng, Yusen Zhang, Tao Yu +2
EMNLP 2021system demonstrations

Recent advances in summarization provide models that can generate summaries of higher quality. Such models now exist for a number of summarization tasks, including query-based summarization, dialogue summarization, and multi-document summarization. While such models and tasks are rapidly growing in…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗