Papers by Philippe Laban
MixQG: Neural Question Generation with Mixed Answer Types (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing neural question generation approaches focus on short factoid type of answers. |
| Approach: | They propose a neural question generator that trains a single generative model by combining multiple question types with different answer types. |
| Outcome: | The proposed model outperforms existing models in both seen and unseen domains and can generate questions with different cognitive levels when conditioned on different answer types. |
Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding (2025.findings-acl)
Copied to clipboard
| Challenge: | Vision Language Models struggle with visual arithmetic, seemingly simple tasks like object counting or length comparison, which are essential for relevant complex tasks like chart understanding and geometric reasoning. |
| Approach: | They propose a novel post-training strategy inspired by Piaget’s theory of cognitive development that trains VLMs to recognize invariant properties under visual transformations. |
| Outcome: | The proposed approach outperforms supervised fine-tuning methods while requiring 60% less training data. |
SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages (2023.acl-long)
Copied to clipboard
| Challenge: | Prior work on document-level simplification has focused on sentence-level edits, while many desirable edits require document- level context. |
| Approach: | They propose a dataset that reconstructs the document-level editing process from English Wikipedia to paired Simple Wikipedia articles. |
| Outcome: | The proposed dataset reconstructs the document-level editing process from English Wikipedia (EW) articles to paired Simple Wikipedia (SEW) pages. |
Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in efficient attention mechanisms have led to the expansion of the context length of large language models. |
| Approach: | They propose a procedure to synthesize Haystacks of documents and generate a summary that identifies relevant insights and precisely cites the source documents. |
| Outcome: | The proposed evaluation can score summaries on Coverage and Citation . the proposed evaluation lags human performance estimates by 10+ points on SummHay . |
KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoning (2025.acl-long)
Copied to clipboard
Peiqi Sui, Juan Diego Rodriguez, Philippe Laban, J. Dean Murphy, Joseph P. Dexter, Richard Jean So, Samuel Baker, Pramit Chaudhuri
| Challenge: | a study of close reading skills in large language models (LLMs) shows that LLMs still lag behind human evaluators on 10 of 11 tasks. |
| Approach: | They propose a benchmark to evaluate close reading skills in large language models . they propose three tasks to approximate different elements of the close reading process . |
| Outcome: | The proposed benchmarks show that state-of-the-art LLMs possess some college-level close reading competency, but performance still trails human evaluators on 10 out of 11 tasks. |
News Headline Grouping as a Challenging NLU Task (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent advances in Natural Language Understanding (NLU) have seen models outperform human performance on many standard tasks. |
| Approach: | They propose a task of HeadLine Grouping and a dataset consisting of 20,056 pairs of news headlines, each labeled with a binary judgement as to whether the pair belongs within the same group. |
| Outcome: | The proposed model outperforms human models on a task consisting of 20,056 pairs of headlines on HLGD and a dataset with a binary judgement. |
Can Transformer Models Measure Coherence In Text: Re-Thinking the Shuffle Test (2021.acl-short)
Copied to clipboard
| Challenge: | Recent work shows that modern NLP models can detect shuffled text without supervision. |
| Approach: | They propose to use Shuffle Test to evaluate whether NLP models can measure coherence in text . they argue that this is unlikely to lead to a good model of text coherency . |
| Outcome: | The Shuffle Test is the most common task to evaluate whether NLP models can measure coherence in text. |
Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text (2021.acl-long)
Copied to clipboard
| Challenge: | a novel approach to text simplification learns to balance a reward across three properties: fluency, salience and simplicity. |
| Approach: | They propose a novel algorithm to optimize the reward which proposes several candidate simplifications and a realistic text comprehension task as an evaluation method for text simplification. |
| Outcome: | The proposed model outperforms strong supervised baselines on the English news domain and can help people complete a comprehension task an average of 18% faster while retaining accuracy. |
Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors (2023.acl-long)
Copied to clipboard
Liyan Tang, Tanya Goyal, Alex Fabbri, Philippe Laban, Jiacheng Xu, Semih Yavuz, Wojciech Kryscinski, Justin Rousseau, Greg Durrett
| Challenge: | Abstractive summarization systems still include factual errors in generated summaries despite recent improvements in factuality detection . |
| Approach: | They aggregate factuality error annotations from nine existing datasets and stratify them according to the underlying summarization model. |
| Outcome: | The proposed method improves on the ChatGPT-based model and shows that it is not superior for all error types. |
Quiz Design Task: Helping Teachers Create Quizzes with Automated Question Generation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Question generation models are often evaluated with standardized NLG metrics that are based on n-gram overlap. |
| Approach: | They propose to use QGen to help teachers automate the generation of reading comprehension quizzes by comparing n-gram overlap with BLEU to compare system-generated questions with heldout human-written references. |
| Outcome: | The best model had only 68.4% of its questions accepted by the ten teachers who participated in the study. |
Creative Planning with Language Models: Practice, Evaluation and Applications (2025.naacl-tutorial)
Copied to clipboard
| Challenge: | This tutorial explores how planning has been learned and deployed in creative workflows . many human creative tasks involve extensive planning, and actions need to be taken . |
| Approach: | This tutorial explores how planning has been learned and deployed in creative workflows . authors discuss forward and backward learning approaches for planning in LLMs - and evaluation metrics tailored to latent plans . |
| Outcome: | This tutorial examines how planning has been learned and deployed in creative workflows . it discusses forward and backward learning approaches for planning in LLMs - evaluation metrics tailored to latent plans . |
What’s The Latest? A Question-driven News Chatbot (2020.acl-demos)
Copied to clipboard
| Challenge: | a news chatbot that draws content from news articles creates conversations with a user about the news. |
| Approach: | They describe an automatic news chatbot that draws content from a diverse set of news sources and creates conversations with a user about the news. |
| Outcome: | The proposed system engages news readers in multi-turn conversations about specific stories. |
SummEdits: Measuring LLM Ability at Factual Reasoning Through The Lens of Summarization (2023.emnlp-main)
Copied to clipboard
Philippe Laban, Wojciech Kryscinski, Divyansh Agarwal, Alexander Fabbri, Caiming Xiong, Shafiq Joty, Chien-Sheng Wu
| Challenge: | Existing factual consistency benchmarks are inadequate to detect factual inconsistencies in LLMs. |
| Approach: | They propose a protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. |
| Outcome: | The proposed method is 20 times more cost-effective per sample and highly reproducible, as it estimates inter-annotator agreement at about 0.9. |
The Summary Loop: Learning to Write Abstractive Summaries Without Examples (2020.acl-main)
Copied to clipboard
| Challenge: | Unsupervised abstractive summarization is important for news headlines and research papers . a novel method that encourages the inclusion of key terms from the original document into the summary is presented . |
| Approach: | They propose a method that encourages the inclusion of key terms from the original document into the summary by a coverage model along with a fluency model. |
| Outcome: | The proposed method outperforms existing methods on news summarization datasets and is competitive with existing methods. |
Prompt Leakage effect and mitigation strategies for multi-turn LLM Applications (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Prompt leakage poses a compelling security and privacy threat in LLM applications. |
| Approach: | They propose a model which leverages the LLM sycophancy effect and a threat model which fine tunes an open-source model to defend against prompt leakage attempts. |
| Outcome: | The proposed model elevates the average attack success rate (ASR) from 17.7% to 86.2% in a multi-turn setting. |
INTELMO: Enhancing Models’ Adoption of Interactive Interfaces (2023.emnlp-demo)
Copied to clipboard
| Challenge: | INTELMO is an easy-to-use library to help model developers adopt user-faced interactive interfaces for their language models. |
| Approach: | They propose a library to help model developers adopt user-faced interactive interfaces and articles from real-time RSS sources for their language models. |
| Outcome: | The proposed library categorizes common NLP tasks and provides default style patterns . it provides developers with fine-grained and flexible control over user interfaces . |
Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Large language models have shown impressive performance in following natural language instructions to solve unseen tasks. |
| Approach: | They propose two strategies to help large language models better leverage task instructions . they propose to remove 60% of tokens from the task definitions while maintaining model performance . |
| Outcome: | The proposed approach achieves 4.2 Rouge-L improvement over 119 unseen test tasks. |
Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles (2024.naacl-long)
Copied to clipboard
Kung-Hsiang Huang, Philippe Laban, Alexander Fabbri, Prafulla Kumar Choubey, Shafiq Joty, Caiming Xiong, Chien-Sheng Wu
| Challenge: | Existing studies on multi-document summarization focus on collating information that all sources agree upon, but the task of summarizing diverse information remains underexplored. |
| Approach: | They propose a task of summarizing diverse information encountered in multiple news articles encompassing the same event using a dataset curated by a large language model. |
| Outcome: | The proposed task aims to summarize diverse information in multiple news articles encompassing the same event . the proposed task is difficult due to its limited coverage and verbosity biases . |
MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents (2024.emnlp-main)
Copied to clipboard
| Challenge: | Current methods for fact-checking are based on verifying each piece of a model against potential evidence using an LLM. |
| Approach: | They propose a method that builds small fact-checking models that have GPT-4-level performance but 400x lower cost. |
| Outcome: | The proposed model outperforms other models and reaches GPT-4 accuracy. |
SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization (2022.tacl-1)
Copied to clipboard
| Challenge: | Recent studies have shown that even state-of-the-art pre-trained language models can generate inconsistent summaries in more than 70% of all cases. |
| Approach: | They propose a method that enables NLI models to be used for inconsistency detection by segmenting documents into sentence units and aggregating scores between pairs of sentences. |
| Outcome: | The proposed method achieves state-of-the-art accuracy of 74.4% on six large inconsistency detection datasets. |
Discord Questions: A Computational Approach To Diversity Analysis in News Coverage (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Modern news aggregators do the hard work of organizing the news, but choosing which source to read remains challenging. |
| Approach: | They propose a framework to help readers identify source differences and gain an understanding of news coverage diversity by generating questions with a diverse answer pool and reusing existing methods. |
| Outcome: | The proposed framework improves performance from current question generation methods by 5% and achieves 81% balanced accuracy on a realistic test set. |
CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments (2025.naacl-long)
Copied to clipboard
Kung-Hsiang Huang, Akshara Prabhakar, Sidharth Dhawan, Yixin Mao, Huan Wang, Silvio Savarese, Caiming Xiong, Philippe Laban, Chien-Sheng Wu
| Challenge: | Existing benchmarks for evaluating CRM agents on work-related tasks are limited due to data privacy concerns. |
| Approach: | They propose a benchmark to evaluate AI agents on real-world CRM tasks . they use 16 commonly used industrial objects with high interconnectivity to simulate real data distributions. |
| Outcome: | The new benchmark evaluates AI agents on real-world customer service tasks . it includes 16 commonly used industrial objects with high interconnectivity . the results highlight the need for enhanced agent capabilities in function-calling and rule-following . |
Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing evaluations of retrieval-augmented generation systems are limited . sub-question coverage measures how well a RAG system addresses different facets of a question. |
| Approach: | They propose a framework for evaluation based on sub-question coverage . they propose to decompose questions into sub-questions and classify them into three types . |
| Outcome: | The proposed evaluation framework measures how well a RAG system addresses different facets of a question. |
Automatic and Human-AI Interactive Text Generation (with a focus on Text Simplification and Revision) (2024.acl-tutorials)
Copied to clipboard
| Challenge: | In this tutorial, we focus on text-to-text generation, a class of natural language generation tasks, that takes a piece of text as input and then generates a revision that is improved according to some specific criteria. |
| Approach: | This tutorial focuses on text-to-text generation, a class of natural language generation tasks that takes a piece of text as input and generates a revision that is improved according to some specific criteria. |
| Outcome: | This tutorial focuses on text-to-text generation, a class of natural language generation tasks, that takes a piece of text as input and generates a revision that is improved according to some specificcriteria. |
Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing conversational recommender systems focus on a single-shot approach to understand user preferences and provide recommendations. |
| Approach: | They propose a problem space for conversational agents that aim to provide both product recommendations and educational value through mixed-type mixed-initiative dialog. |
| Outcome: | The proposed framework can simulate salesbot and shopperbot agents and provide both product recommendations and educational value through mixed-type mixed-initiative dialog. |
Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluating progress in natural language generation tasks are expensive, difficult to reproduce, and non-reusable. |
| Approach: | They propose a new automatic evaluation method for NLG called Near-Negative Distinction that repurposes prior human annotations into NND tests. |
| Outcome: | The proposed method achieves higher correlation with human judgments than standard NLG evaluation metrics. |