Author name cluster

Ahmed Hassan Awadallah

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

ICLR Conference 2025 Conference Paper

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

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 this problem by proposing a novel algorithm, *Exploratory Preference Optimization* (XPO). This algorithm is elegantly simple---requiring only a one-line modification to (online) Direct Preference Optimization (DPO; Rafailov et al., 2023)---yet provides the strongest known provable guarantees. XPO augments the DPO objective with a novel and principled *exploration bonus*, enabling the algorithm to strategically explore beyond the support of the initial model and preference feedback data. We prove that XPO is provably sample-efficient and converges to a near-optimal policy under natural exploration conditions, regardless of the initial model's coverage. Our analysis builds on the observation that DPO implicitly performs a form of *Bellman error minimization*. It synthesizes previously disparate techniques from language modeling and theoretical reinforcement learning in a serendipitous fashion through the lens of *KL-regularized Markov decision processes*.

Details

AAAI Conference 2025 Conference Paper

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

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. Our proposed system identifies relevant skills embedded in different groups of prompts and dynamically weighs experts (i.e., collection of prompts) based on the target task. Experiments show that MoPs are resilient to model compression, data source, and task composition, making them highly versatile and applicable in various contexts. In practice, MoPs can simultaneously mitigate prompt training ``interference'' in multi-task, multi-source scenarios (e.g., task and data heterogeneity across sources) and possible implications from model approximations. Empirically, MoPs show particular effectiveness in compressed model scenarios, while maintaining favorable performance in uncompressed settings: MoPs can reduce final perplexity from 9% up to 70% in non-i.i.d. distributed cases and from 3% up to 30% in centralized cases, compared to baselines.

PDF Details DOI

TMLR Journal 2024 Journal Article

CR-MoE: Consistent Routed Mixture-of-Experts for Scaling Contrastive Learning

Ziyu Jiang
Guoqing Zheng
Yu Cheng
Ahmed Hassan Awadallah
Zhangyang Wang

While Contrastive Learning (CL) achieves great success in many downstream tasks, its good performance heavily relies on a large model capacity. As previous methods focus on scaling dense models, training and inference costs increase rapidly with model sizes, leading to large resource consumption. In this paper, we explore CL with an efficient scaling method, Mixture of Experts (MoE), to obtain a large but sparse model. We start by plugging in the state-of-the-art CL method to MoE. However, this naive combination fails to visibly improve performance despite a much larger capacity. A closer look reveals that the naive MoE+CL model has a strong tendency to route two augmented views of the same image token to different subsets of experts: such ``cross-view instability" breaks the weight-sharing nature in CL and misleads the invariant feature learning. To address this issue, we introduce a new regularization mechanism, by enforcing expert-routing similarity between different views of the same image (or its overlapped patch tokens), while promoting expert-routing diversity of patches from different images. The resultant method, called CR-MoE, improves by 1.7 points in terms of 1\% semi-supervised learning accuracy on ImageNet, compared to the naive combination baseline. It further surpasses the state-of-the-art CL methods on ImageNet pre-training of Vision Transformer (ViT) by 2.8 points, at the same computational cost. Our findings validate CR-MoE as an effective and efficient image representation learner. Code is available at https://github.com/VITA-Group/CRMoE.

PDF Details

ICLR Conference 2024 Conference Paper

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

Dujian Ding
Ankur Mallick
Chi Wang 0001
Robert Sim
Subhabrata Mukherjee
Victor Rühle
Laks V. S. Lakshmanan
Ahmed Hassan Awadallah

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 inference approach which combines their respective strengths to save cost and maintain quality. Our approach uses a router that assigns queries to the small or large model based on the predicted query difficulty and the desired quality level. The desired quality level can be tuned dynamically at test time to seamlessly trade quality for cost as per the scenario requirements. In experiments our approach allows us to make up to 40% fewer calls to the large model, with no drop in response quality.

Details

ICLR Conference 2024 Conference Paper

Teaching Language Models to Hallucinate Less with Synthetic Tasks

Erik Jones
Hamid Palangi
Clarisse Simões
Varun Chandrasekaran
Subhabrata Mukherjee
Arindam Mitra
Ahmed Hassan Awadallah
Ece Kamar

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 challenging, as hallucination is hard to efficiently, cheaply, and reliably evaluate at each optimization step. In this work, we show that reducing hallucination on a _synthetic task_ can also reduce hallucination on real-world downstream tasks. Our method, SynTra, first designs a synthetic task where hallucinations are easy to elicit and measure. It next optimizes the LLM's system message via prefix tuning on the synthetic task, then uses the system message on realistic, hard-to-optimize tasks. Across three realistic abstractive summarization tasks, we reduce hallucination for two 13B-parameter LLMs using supervision signal from only a synthetic retrieval task. We also find that optimizing the system message rather than the model weights can be critical; fine-tuning the entire model on the synthetic task can counterintuitively _increase_ hallucination. Overall, SynTra demonstrates that the extra flexibility of working with synthetic data can help mitigate undesired behaviors in practice.

Details

ICLR Conference 2022 Conference Paper

Knowledge Infused Decoding

Ruibo Liu
Guoqing Zheng
Shashank Gupta
Radhika Gaonkar
Chongyang Gao
Soroush Vosoughi
Milad Shokouhi
Ahmed Hassan Awadallah

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 when used in knowledge-intensive natural language generation (NLG) tasks. Recent remedies to this problem focus on modifying either the pre-training or task fine-tuning objectives to incorporate knowledge, which normally require additional costly training or architecture modification of LMs for practical applications. We present Knowledge Infused Decoding (KID)---a novel decoding algorithm for generative LMs, which dynamically infuses external knowledge into each step of the LM decoding. Specifically, we maintain a local knowledge memory based on the current context, interacting with a dynamically created external knowledge trie, and continuously update the local memory as a knowledge-aware constraint to guide decoding via reinforcement learning. On six diverse knowledge-intensive NLG tasks, task-agnostic LMs (e.g., GPT-2 and BART) armed with KID outperform many task-optimized state-of-the-art models, and show particularly strong performance in few-shot scenarios over seven related knowledge-infusion techniques. Human evaluation confirms KID's ability to generate more relevant and factual language for the input context when compared with multiple baselines. Finally, KID also alleviates exposure bias and provides stable generation quality when generating longer sequences.

Details

IS Journal 2021 Journal Article

Detecting Fake News With Weak Social Supervision

Kai Shu
Susan Dumais
Ahmed Hassan Awadallah
Huan Liu

Limited labeled data are becoming one of the largest bottlenecks for supervised learning systems. This is especially the case for many real-world tasks, where large-scale labeled examples are either too expensive to acquire or unavailable due to privacy or data access constraints. Weak supervision has shown to be effective in mitigating the scarcity of labeled data by leveraging weak labels or injecting constraints from heuristic rules and/or extrinsic knowledge sources. Social media has little labeled data but possesses unique characteristics that make it suitable for generating weak supervision, resulting in a new type of weak supervision, i. e. , weak social supervision. In this article, we illustrate how various aspects of social media can be used as weak social supervision. Specifically, we use the recent research on fake news detection as the use case, where social engagements are abundant but annotated examples are scarce, to show that weak social supervision is effective when facing the labeled data scarcity problem. This article opens the door to learning with weak social supervision for similar emerging tasks when labeled data are limited.

Details DOI

AAAI Conference 2021 Conference Paper

Meta Label Correction for Noisy Label Learning

Guoqing Zheng
Ahmed Hassan Awadallah
Susan Dumais

Leveraging weak or noisy supervision for building effective machine learning models has long been an important research problem. Its importance has further increased recently due to the growing need for large-scale datasets to train deep learning models. Weak or noisy supervision could originate from multiple sources including non-expert annotators or automatic labeling based on heuristics or user interaction signals. There is an extensive amount of previous work focusing on leveraging noisy labels. Most notably, recent work has shown impressive gains by using a meta-learned instance re-weighting approach where a meta-learning framework is used to assign instance weights to noisy labels. In this paper, we extend this approach via posing the problem as a label correction problem within a meta-learning framework. We view the label correction procedure as a meta-process and propose a new meta-learning based framework termed MLC (Meta Label Correction) for learning with noisy labels. Specifically, a label correction network is adopted as a meta-model to produce corrected labels for noisy labels while the main model is trained to leverage the corrected labels. Both models are jointly trained by solving a bi-level optimization problem. We run extensive experiments with different label noise levels and types on both image recognition and text classification tasks. We compare the re-weighing and correction approaches showing that the correction framing addresses some of the limitations of re-weighting. We also show that the proposed MLC approach outperforms previous methods in both image and language tasks.

PDF Details

ICLR Conference 2021 Conference Paper

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

Tao Yu 0009
Rui Zhang 0037
Alex Polozov
Christopher Meek
Ahmed Hassan Awadallah

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 relation between the unstructured language utterance and the structured ontology while representing the multi-turn dynamics of the dialog. Pre-trained language models (LMs) are the state-of-the-art for various natural language processing tasks. However, existing pre-trained LMs that use language modeling training objectives over free-form text have limited ability to represent natural language references to contextual structural data. In this work, we present SCORE, a new pre-training approach for CSP tasks designed to induce representations that capture the alignment between the dialogue flow and the structural context. We demonstrate the broad applicability of SCORE to CSP tasks by combining SCORE with strong base systems on four different tasks (SPARC, COSQL, MWOZ, and SQA). We show that SCORE can improve the performance over all these base systems by a significant margin and achieves state-of-the-art results on three of them.

Details

AAAI Conference 2019 Conference Paper

Adversarial Training for Community Question Answer Selection Based on Multi-Scale Matching

Xiao Yang
Madian Khabsa
Miaosen Wang
Wei Wang
Ahmed Hassan Awadallah
Daniel Kifer
C. Lee Giles

Community-based question answering (CQA) websites represent an important source of information. As a result, the problem of matching the most valuable answers to their corresponding questions has become an increasingly popular research topic. We frame this task as a binary (relevant/irrelevant) classification problem, and present an adversarial training framework to alleviate label imbalance issue. We employ a generative model to iteratively sample a subset of challenging negative samples to fool our classification model. Both models are alternatively optimized using REIN- FORCE algorithm. The proposed method is completely different from previous ones, where negative samples in training set are directly used or uniformly down-sampled. Further, we propose using Multi-scale Matching which explicitly inspects the correlation between words and ngrams of different levels of granularity. We evaluate the proposed method on SemEval 2016 and SemEval 2017 datasets and achieves state-of-the-art or similar performance.

PDF Details