31 citations · 46 across the 15 of their papers we have counts for
18 papers
Co-Evolving Actor-Conditioned Critics for Non-Verifiable Generation
Jinyoung Kim, Muhammad Khalifa, Lajanugen Logeswaran +4
Natural-language critiques provide supervision beyond scalar rewards for non-verifiable generation, which lacks deterministic verifiers. In critique-guided refinement, a critic giv…
Process Reward Models That Think
Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran +5
Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling. PRMs require step-level supervision, making them expensive to tr…
If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs
Muhammad Khalifa, Yi-Chern Tan, Arash Ahmadian +6
Model merging has shown great promise at combining expert models, but the benefit of merging is unclear when merging "generalist" models trained on many tasks. We explore merging i…
Small Language Models Need Strong Verifiers to Self-Correct Reasoning
Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran +4
Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs), where LLMs refine their solutions using self-generated criti…
Exploring Demonstration Ensembling for In-context Learning
Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee +2
In-context learning (ICL) operates by showing language models (LMs) examples of input-output pairs for a given task, i.e., demonstrations. The standard approach for ICL is to promp…
BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases
Xin Liu, Muhammad Khalifa, Lu Wang
Energy-based models (EBMs) have gained popularity for controlled text generation due to their high applicability to a wide range of constraints. However, sampling from EBMs is non-…
GRACE: Discriminator-Guided Chain-of-Thought Reasoning
Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee +2
In the context of multi-step reasoning, e.g., with chain-of-thought, language models (LMs) can easily assign a high likelihood to incorrect steps. As a result, decoding strategies…
Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models
Oana Ignat, Zhijing Jin, Artem Abzaliev +19
Recent progress in large language models (LLMs) has enabled the deployment of many generative NLP applications. At the same time, it has also led to a misleading public discourse t…
Novel Chapter Abstractive Summarization using Spinal Tree Aware Sub-Sentential Content Selection
Hardy Hardy, Miguel Ballesteros, Faisal Ladhak +3
Summarizing novel chapters is a difficult task due to the input length and the fact that sentences that appear in the desired summaries draw content from multiple places throughout…
Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents
Muhammad Khalifa, Yogarshi Vyas, Shuai Wang +3
We investigate semi-structured document classification in a zero-shot setting. Classification of semi-structured documents is more challenging than that of standard unstructured do…
Few-shot Reranking for Multi-hop QA via Language Model Prompting
Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee +2
We study few-shot reranking for multi-hop QA with open-domain questions. To alleviate the need for a large number of labeled question-document pairs for retriever training, we prop…
A Bag of Tricks for Dialogue Summarization
Muhammad Khalifa, Miguel Ballesteros, Kathleen McKeown
Dialogue summarization comes with its own peculiar challenges as opposed to news or scientific articles summarization. In this work, we explore four different challenges of the tas…
Zero-Resource Multi-Dialectal Arabic Natural Language Understanding
Muhammad Khalifa, Hesham Hassan, Aly Fahmy
A reasonable amount of annotated data is required for fine-tuning pre-trained language models (PLM) on downstream tasks. However, obtaining labeled examples for different language…
Self-Training Pre-Trained Language Models for Zero- and Few-Shot Multi-Dialectal Arabic Sequence Labeling
Muhammad Khalifa, Muhammad Abdul-Mageed, Khaled Shaalan
A sufficient amount of annotated data is usually required to fine-tune pre-trained language models for downstream tasks. Unfortunately, attaining labeled data can be costly, especi…
A Distributional Approach to Controlled Text Generation
Muhammad Khalifa, Hady Elsahar, Marc Dymetman
We propose a Distributional Approach for addressing Controlled Text Generation from pre-trained Language Models (LMs). This approach permits to specify, in a single formal framewor…
Extracting Synonyms from Bilingual Dictionaries
Mustafa Jarrar, Eman Karajah, Muhammad Khalifa +1
We present our progress in developing a novel algorithm to extract synonyms from bilingual dictionaries. Identification and usage of synonyms play a significant role in improving t…
Book Success Prediction with Pretrained Sentence Embeddings and Readability Scores
Muhammad Khalifa, Aminul Islam
Predicting the potential success of a book in advance is vital in many applications. This could help both publishers and readers in their decision-making process whether or not a b…
Semantic Source Code Search: A Study of the Past and a Glimpse at the Future
Muhammad Khalifa
With the recent explosion in the size and complexity of source codebases and software projects, the need for efficient source code search engines has increased dramatically. Unfort…