Large language models (LLMs) have shown impressive multilingual capabilities through pretraining on diverse corpora. While these models show strong reasoning abilities, their performance varies significantly across languages due to imbalanced training data distribution. Existing approaches using sample-level translation for extensive multilingual pretraining and cross-lingual tuning face scalability challenges and often fail to capture nuanced reasoning processes across languages. In this paper, we introduce **AdaMCoT** (Adaptive Multilingual Chain-of-Thought), a framework that enhances multilingual factual reasoning by dynamically routing thought processes in intermediary “thinking languages” before generating target-language responses. AdaMCoT leverages a language-agnostic core and incorporates an adaptive, reward-based mechanism for selecting optimal reasoning pathways without requiring additional pretraining. Our comprehensive evaluation across multiple benchmarks demonstrates substantial improvements in both factual reasoning quality and cross-lingual consistency, with particularly strong performance gains in low-resource language settings. An in-depth analysis of the model’s hidden states and semantic space further elucidates the underlying mechanism of our method. The results suggest that adaptive reasoning paths can effectively bridge the performance gap between high- and low-resource languages while maintaining cultural and linguistic nuances.

Multi-constraint planning involves identifying, evaluating, and refining candidate plans while satisfying multiple, potentially conflicting constraints.Existing large language model (LLM) approaches face fundamental limitations in this domain.Pure reasoning paradigms, which rely on long natural language chains, are prone to inconsistency, error accumulation, and prohibitive cost as constraints compound.Conversely, LLMs combined with coding-or solver-based strategies lack flexibility: they often generate problem-specific code from scratch or depend on fixed solvers, failing to capture generalizable logic across diverse problems.To address these challenges, we introduce the Scalable COde Planning Engine (SCOPE), a framework that disentangles query-specific reasoning from generic code execution.By separating reasoning from execution, SCOPE produces solver functions that are consistent, deterministic, and reusable across queries while requiring only minimal changes to input parameters.SCOPE achieves state-of-the-art performance while lowering cost and latency.For example, with GPT-4o, it reaches 93.1% success on TravelPlanner, a 61.6% gain over the best baseline (CoT) while cutting inference cost by 1.4x and time by 4.67x.Code is available at https://github.com/DerrickGXD/SCOPE.

Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Roy Ka-Wei Lee. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

We present a conceptual framework for analyzing dialogue in collaborative problem-solving contexts, with an emphasis on the emerging dynamics of human-AI and multi-agent collaboration. As intelligent systems become active agents capable of autonomous reasoning and strategic cooperation, understanding the dialogic interaction during collaborative problem solving is increasingly important for optimizing and evaluating such partnerships. Our framework addresses key limitations in current analytical approaches through a hierarchical two-layer coding scheme that integrates cognitive and non-cognitive problem solving with metacognitive regulatory mechanisms. We demonstrate its effectiveness and generalizability across nine datasets spanning multiple domains, and provide insights into how humans and agents coordinate their knowledge, skills, and efforts to solve complex problems, showing in particular that metacognitive regulation can be an essential discriminator of deeper collaboration.

We introduce SagaQA, a long-form video benchmark for multi-hop reasoning over full-length TV series. Existing video reasoning benchmarks often emphasize local understanding of adjacent frames or clips. SagaQA addresses this gap by requiring high-level comprehension of extended multimodal narratives in entire TV shows. A distinguishing feature of SagaQA is the granularity of its reasoning steps. Our dataset necessitates long-range reasoning hops to connect information across completely different episodes. This requires models to reason over entire events and actions, demanding a deep understanding of the show’s narration and progression at a multimodal level. Motivated by recent progress in agentic methods, we further study how different planning strategies handle such complex reasoning. We categorize these approaches into three classes—parallel, sequential, and hybrid planners—and evaluate their ability to generate coherent and complete reasoning plans. Our results on SagaQA suggest that hybrid planners consistently produce higher-quality plans and exhibit stronger capabilities for complex, high-level narrative understanding in TV shows.

Multilingual Large Language Models (LLMs) struggle with cross-lingual tasks due to data imbalances between high-resource and low-resource languages and the monolingual bias in pre-training. Existing methods, such as bilingual fine-tuning and contrastive alignment, improve cross-lingual performance but often require extensive parallel data or suffer from instability. To address these challenges, we introduce a Cross-Lingual Mapping Task in the pre-training phase, which enhances cross-lingual alignment without compromising monolingual fluency. Our approach bi-directionally maps languages within the LLM’s embedding space, improving both language generation and comprehension. We further introduce a Language Alignment Coefficient to robustly quantify cross-lingual consistency, even in limited-data scenarios. Experimental results on machine translation (MT), cross-lingual natural language understanding (CLNLU), and cross-lingual question answering (CLQA) show that our model achieves up to 11.9 BLEU score gains in MT, an increase of 6.72 in CLQA BERTScore-Precision and more than a 5% increase in CLNLU accuracy over strong multilingual baselines. Our findings highlight the potential of embedding cross-lingual objectives into pre-training, improving multilingual LLMs.

Human-machine collaborative compression has been receiving increasing research efforts for reducing image/video data, serving as the basis for both human perception and machine intelligence. Existing collaborative methods are dominantly built upon the de facto human-vision compression pipeline, witnessing deficiency on complexity and bit-rates when aggregating the machine-vision compression. Indeed, machine vision solely focuses on the core regions within the image/video, requiring much less information compared with the compressed information for human vision. In this paper, we thus set out the first successful attempt by a novel collaborative compression method based on the machine-vision-oriented compression, instead of human-vision pipeline. In other words, machine vision serves as the basis for human vision within collaborative compression. A plug-and-play variable bit-rate strategy is also developed for machine vision tasks. Then, we propose to progressively aggregate the semantics from the machine-vision compression, whilst seamlessly tailing the diffusion prior to restore high-fidelity details for human vision, thus named as diffusion-prior based feature compression for human and machine visions (Diff-FCHM). Experimental results verify the consistently superior performances of our Diff-FCHM, on both machine-vision and human-vision compression with remarkable margins. The source code is available at https://github.com/bblgbr/Diff-FCHM.

The acceleration of Large Language Models (LLMs) research has opened up new possibilities for evaluating generated text. Though LLMs serve as scalable and economical evaluators, how reliable these evaluators is still under-explored. Prior research efforts in the meta-evaluation of LLMs as judges limit the prompting of an LLM to a single use to obtain a final evaluation decision. They then compute the agreement between LLMs’ outputs and human labels. This lacks interpretability in understanding the evaluation capability of LLMs. In light of this challenge, we propose DnA-Eval, which breaks down the evaluation process into decomposition and aggregation stages based on pedagogical practices. Our experiments show that it not only provides a more interpretable window for how well LLMs evaluate, but also leads to improvements up to 39.6% for different LLMs on a variety of meta-evaluation benchmarks.

Large Language Models (LLMs) can struggle to balance gullibility to misinformation and resistance to valid corrections in persuasive dialogues, a critical challenge for reliable deployment.We introduce DuET-PD (Dual Evaluation for Trust in Persuasive Dialogues), a framework evaluating multi-turn stancechange dynamics across dual dimensions: persuasion type (corrective/misleading) and domain (knowledge via MMLU-Pro, and safety via SALAD-Bench).We find that even a stateof-the-art model like GPT-4o achieves only 27.32% accuracy in MMLU-Pro under sustained misleading persuasions.Moreover, results reveal a concerning trend of increasing sycophancy in newer open-source models.To address this, we introduce Holistic DPO, a training approach balancing positive and negative persuasion examples.Unlike prompting or resist-only training, Holistic DPO enhances both robustness to misinformation and receptiveness to corrections, improving Llama-3.1-8B-Instruct'saccuracy under misleading persuasion in safety contexts from 4.21% to 76.54%.These contributions offer a pathway to developing more reliable and adaptable LLMs for multi-turn dialogue.Code is available at https://github.com/Social-AI-Studio/DuET-PD.

Pair programming is a collaborative activity that enhances students' computational thinking (CT) skills. Analyzing students' interactions during pair programming provides valuable insights into effective learning. However, interpreting classroom dialogues is a challenging and complex task. Due to the simultaneous interaction between interlocutors and other ambient noise in collaborative learning contexts, previous work heavily relied on manual transcription and coding, which is labor-intensive and time-consuming. Recent advancements in speech and language processing offer promising opportunities to automate and scale up dialogue analysis. Besides, previous work mainly focused on task-related interactions, with little attention to social interactions. To address these gaps, we conducted a four-week CT course with 26 fifth-grade primary school students. We recorded their discussions, transcribed them with speech processing models, and developed a coding scheme and applied LLMs for annotation. Our AI-driven pipeline effectively analyzed classroom recordings with high accuracy and efficiency. After identifying the dialogue patterns, we investigated the relationships between these patterns and CT performance. Four clusters of dialogue patterns have been identified: Inquiry, Constructive Collaboration, Disengagement, and Disputation. We observed that Inquiry and Constructive Collaboration patterns were positively related to students' CT skills, while Disengagement and Disputation patterns were associated with lower CT performance. This study contributes to the understanding of how dialogue patterns relate to CT performance and provides implications for both research and educational practice in CT learning.

Bin Wang, Xunlong Zou, Geyu Lin, Shuo Sun, Zhuohan Liu, Wenyu Zhang, Zhengyuan Liu, AiTi Aw, Nancy F. Chen. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Large Language Models (LLMs) have demonstrated significant potential in handling complex reasoning tasks through step-by-step rationale generation.However, recent studies have raised concerns regarding the hallucination and flaws in their reasoning process.Substantial efforts are being made to improve the reliability and faithfulness of the generated rationales.Some approaches model reasoning as planning, while others focus on annotating for process supervision.Nevertheless, the planning-based search process often results in high latency due to the frequent assessment of intermediate reasoning states and the extensive exploration space.Additionally, supervising the reasoning process with human annotation is costly and challenging to scale for LLM training.To address these issues, in this paper, we propose a framework to learn planning-based reasoning through Direct Preference Optimization (DPO) on collected trajectories, which are ranked according to our synthesized process rewards.Our results on challenging logical reasoning benchmarks demonstrate the effectiveness of our learning framework, showing that our 7B model can surpass the strong counterparts like GPT-3.5-Turbo.

Intelligent Tutoring Systems (ITSs) can provide personalized and self-paced learning experience.The emergence of large language models (LLMs) further enables better humanmachine interaction, and facilitates the development of conversational ITSs in various disciplines such as math and language learning.In dialogic teaching, recognizing and adapting to individual characteristics can significantly enhance student engagement and learning efficiency.However, characterizing and simulating student's persona remain challenging in training and evaluating conversational ITSs.In this work, we propose a framework to construct profiles of different student groups by refining and integrating both cognitive and noncognitive aspects, and leverage LLMs for personalityaware student simulation in a language learning scenario.We further enhance the framework with multi-aspect validation, and conduct extensive analysis from both teacher and student perspectives.Our experimental results show that state-of-the-art LLMs can produce diverse student responses according to the given language ability and personality traits, and trigger teacher's adaptive scaffolding strategies.

Fangkai Jiao, Zhiyang Teng, Bosheng Ding, Zhengyuan Liu, Nancy Chen, Shafiq Joty. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Bin Wang, Zhengyuan Liu, Xin Huang, Fangkai Jiao, Yang Ding, AiTi Aw, Nancy Chen. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Large language models demonstrate remarkable proficiency in various tasks across multiple languages.However, their potential in codeswitching remains underexplored, particularly in cultural and educational contexts.Codeswitching or translanguaging plays a crucial role in bilingual education, facilitating comprehension and engagement among students with varied language proficiency.In this work, we present a pedagogy-inspired framework that introduces traditional classroom practices of code-switching to intelligent tutoring systems.Specifically, we develop fine-grained instructional strategies tailored to multilingual and educational needs.We conduct experiments involving both LLM-based evaluation and expert analysis to assess the effectiveness of translanguaging in tutoring dialogues.Our experimental results indicate that strategic code-switching can significantly enhance the learning experience.This work not only advances dialogic tutors in language learning but also extends LLMs to better accommodate multilingual interaction.

Stance detection determines whether the author of a piece of text is in favor of, against, or neutral towards a specified target, and can be used to gain valuable insights into social media.The ubiquitous indirect referral of targets makes this task challenging, as it requires computational solutions to model semantic features and infer the corresponding implications from a literal statement.Moreover, the limited amount of available training data leads to subpar performance in out-of-domain and cross-target scenarios, as data-driven approaches are prone to rely on superficial and domain-specific features.In this work, we decompose the stance detection task from a linguistic perspective, and investigate key components and inference paths in this task.The stance triangle is a generic linguistic framework previously proposed to describe the fundamental ways people express their stance.We further expand it by characterizing the relationship between explicit and implicit objects.We then use the framework to extend one single training corpus with additional annotation.Experimental results show that strategically-enriched data can significantly improve the performance on out-of-domain and cross-target evaluation.

Kexin Yang, Dayiheng Liu, Wenqiang Lei, Baosong Yang, Xiangpeng Wei, Zhengyuan Liu, Jun Xie. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Annotated data plays a critical role in Natural Language Processing (NLP) in training models and evaluating their performance.Given recent developments in Large Language Models (LLMs), models such as ChatGPT demonstrate zero-shot capability on many text-annotation tasks, comparable with or even exceeding human annotators.Such LLMs can serve as alternatives for manual annotation, due to lower costs and higher scalability.However, limited work has leveraged LLMs as complementary annotators, nor explored how annotation work is best allocated among humans and LLMs to achieve both quality and cost objectives.We propose CoAnnotating, a novel paradigm for Human-LLM co-annotation of unstructured texts at scale.Under this framework, we utilize uncertainty to estimate LLMs' annotation capability.Our empirical study shows CoAnnotating to be an effective means to allocate work from results on different datasets, with up to 21% performance improvement over random baseline.For code implementation, see https: //github.com/SALT-NLP/CoAnnotating.

Conventional dialogue summarization methods directly generate summaries and do not consider user's specific interests.This poses challenges in cases where the users are more focused on particular topics or aspects.With the advancement of instruction-finetuned language models, we introduce instruction-tuning to dialogues to expand the capability set of dialogue summarization models.To overcome the scarcity of instructive dialogue summarization data, we propose a three-step approach to synthesize high-quality query-based summarization triples.This process involves summaryanchored query generation, query filtering and query-based summary generation.By training a unified model called InstructDS (Instructive Dialogue Summarization) on three summarization datasets with multi-purpose instructive triples, we expand the capability of dialogue summarization models.We evaluate our method on four datasets, including dialogue summarization and dialogue reading comprehension.Experimental results show that our approach outperforms the state-of-the-art models and even models with larger sizes.Additionally, our model exhibits higher generalizability and faithfulness, as confirmed by human subjective evaluations.Benjamin: Hey guys, what are we doing with the keys today?Hilary: I've got them.Whoever wants

The Transformer-based models with the multi-head self-attention mechanism are widely used in natural language processing, and provide state-of-the-art results. While the pre-trained language backbones are shown to implicitly capture certain linguistic knowledge, explicitly incorporating structure-aware features can bring about further improvement on the downstream tasks. However, such enhancement often requires additional neural components and increases training parameter size. In this work, we investigate the attention head selection and manipulation strategy for feature injection from a network pruning perspective, and conduct a case study on dialogue summarization. We first rank attention heads in a Transformer-based summarizer with layer-wise importance. We then select the underused heads through extensive analysis, and inject structure-aware features by manipulating the selected heads. Experimental results show that the importance-based head selection is effective for feature injection, and dialogue summarization can be improved by incorporating coreference information via head manipulation.

Within the natural language processing community, English is by far the most resource-rich language. There is emerging interest in conducting translation via computational approaches to conform its dialects or creole languages back to standard English. This computational approach paves the way to leverage generic English language backbones, which are beneficial for various downstream tasks. However, in practical online communication scenarios, the use of language varieties is often accompanied by noisy user-generated content, making this translation task more challenging. In this work, we introduce a joint paraphrasing task of creole translation and text normalization of Singlish messages, which can shed light on how to process other language varieties and dialects. We formulate the task in three different linguistic dimensions: lexical level normalization, syntactic level editing, and semantic level rewriting. We build an annotated dataset of Singlish-to-Standard English messages, and report performance on a perturbation-resilient sequence-to-sequence model. Experimental results show that the model produces reasonable generation results, and can improve the performance of downstream tasks like stance detection.

International audience

Although fine-tuning pre-trained backbones produces fluent and grammatically-correct text in various language generation tasks, factual consistency in abstractive summarization remains challenging.This challenge is especially thorny for dialogue summarization, where neural models often make inaccurate associations between personal named entities and their respective actions.To tackle this type of hallucination, we present an entity-based de-noising model via text perturbation on reference summaries.We then apply this proposed approach in beam search validation, conditional training augmentation, and inference post-editing.Experimental results on the SAMSum corpus show that state-of-the-art models equipped with our proposed method achieve generation quality improvement in both automatic evaluation and human assessment.

Abstract This paper proposes a three‐stage algorithm based on clustering decomposition and task allocation—improved clustering planning algorithm (iK‐iD‐N), aiming at the optimization task allocation problem of drones in actual application to meet the task demand constraints. The algorithm solves the problem of the number of drones demanded and the initial delivery range of each drone by introducing dual‐objective planning into the clustering decomposition. Combining improved Dijkstra algorithm (iK‐D) with neighbourhood insertion algorithm into task allocation, to get high‐quality solutions and solve efficiently. Compared with the existing ant colony algorithm, the iK‐iD‐N algorithm proposed in this paper is more efficient and can obtain the best and stable solutions while evenly distributing tasks. Then it is compared with the improved clustering algorithm combined with the basic iK‐D to get better solutions of the iK‐iD‐N algorithm at any time, and compared with the basic clustering algorithm with the improved task allocation algorithm (K‐iD‐N) that iK‐ iD‐N can get a better solution with high probability. The thesis also simulates and analyzes the impact of uncertainty requirements on the solutions based on drone demand and task allocation models, and discusses the impact of drone load capability and endurance capability constraints on the final solutions.

With the development of 5G, the distribution of base stations tends to be dense. Compared with the traditional network architecture, Cloud Radio Access Networks(C-RAN) architecture can satisfy the current requirements of high bandwidth, low latency and low energy consumption. Currently most energy-saving scheme for C-RAN is complex with time cost computing, which may not be suitable for large-scale region. For the problem of energy-efficient resource allocation for dense distribution of Remote Radio Heads(RRHs) in C-RAN, we use K-means clustering algorithm to simplify the network topology and reduce the complexity under a distributed manner. Aiming at the problem of network resource allocation in C-RAN, we use A3C algorithm to allocate network transmission power, and compare the total energy consumption, system energy efficiency and Signal to Interference plus Noise Ratio(SINR) value of terminal devices through simulation experiments. The experimental results show that in the same network environment, A3C algorithm has the highest energy efficiency, and can keep the SINR value of terminal devices in a reasonable range, which proves the effectiveness of A3C algorithm.

In this paper, we propose a controllable neural generation framework that can flexibly guide dialogue summarization with personal named entity planning.The conditional sequences are modulated to decide what types of information or what perspective to focus on when forming summaries to tackle the under-constrained problem in summarization tasks.This framework supports two types of use cases: (1) Comprehensive Perspective, which is a generalpurpose case with no user-preference specified, considering summary points from all conversational interlocutors and all mentioned persons; (2) Focus Perspective, positioning the summary based on a user-specified personal named entity, which could be one of the interlocutors or one of the persons mentioned in the conversation.During training, we exploit occurrence planning of personal named entities and coreference information to improve temporal coherence and to minimize hallucination in neural generation.Experimental results show that our proposed framework generates fluent and factually consistent summaries under various planning controls using both objective metrics and human evaluations.

We introduce a synthetic dialogue generation framework, Velocidapter, which addresses the corpus availability problem for dialogue comprehension.Velocidapter augments datasets by simulating synthetic conversations for a task-oriented dialogue domain, requiring a small amount of bootstrapping work for each new domain.We evaluate the efficacy of our framework on a task-oriented dialogue comprehension dataset, MRCWOZ, which we curate by annotating questions for slots in the restaurant, taxi, and hotel domains of the Mul-tiWOZ 2.2 dataset (Zang et al., 2020).We run experiments within a low-resource setting, where we pretrain a model on SQuAD, fine-tuning it on either a small original data or on the synthetic data generated by our framework.Velocidapter shows significant improvements using both the transformer-based BERT-Base and BiDAF as base models.We further show that the framework is easy to use by novice users and conclude that Velocidapter can greatly help training over task-oriented dialogues, especially for low-resourced emerging domains.

Summarizing conversations via neural approaches has been gaining research traction lately, yet it is still challenging to obtain practical solutions.Examples of such challenges include unstructured information exchange in dialogues, informal interactions between speakers, and dynamic role changes of speakers as the dialogue evolves.Many of such challenges result in complex coreference links.Therefore, in this work, we investigate different approaches to explicitly incorporate coreference information in neural abstractive dialogue summarization models to tackle the aforementioned challenges.Experimental results show that the proposed approaches achieve state-of-the-art performance, implying it is useful to utilize coreference information in dialogue summarization.Evaluation results on factual correctness suggest such coreferenceaware models are better at tracing the information flow among interlocutors and associating accurate status/actions with the corresponding interlocutors and person mentions.

Text discourse parsing plays an important role in understanding information flow and argumentative structure in natural language.Previous research under the Rhetorical Structure Theory (RST) has mostly focused on inducing and evaluating models from the English treebank.However, the parsing tasks for other languages such as German, Dutch, and Portuguese are still challenging due to the shortage of annotated data.In this work, we investigate two approaches to establish a neural, cross-lingual discourse parser via: (1) utilizing multilingual vector representations; and(2) adopting segment-level translation of the source content.Experiment results show that both methods are effective even with limited training data, and achieve state-of-the-art performance on cross-lingual, document-level discourse parsing on all sub-tasks.

Comprehending multi-turn spoken conversations is an emerging research area, presenting challenges different from reading comprehension of passages due to the interactive nature of information exchange from at least two speakers.Unlike passages, where sentences are often the default semantic modeling unit, in multi-turn conversations, a turn is a topically coherent unit embodied with immediately relevant context, making it a linguistically intuitive segment for computationally modeling verbal interactions.Therefore, in this work, we propose a hierarchical attention neural network architecture, combining turnlevel and word-level attention mechanisms, to improve spoken dialogue comprehension performance.Experiments are conducted on a multi-turn conversation dataset, where nurses inquire and discuss symptom information with patients.We empirically show that the proposed approach outperforms standard attention baselines, achieves more efficient learning outcomes, and is more robust to lengthy and out-of-distribution test samples.

Due to the lack of publicly available resources, conversation summarization has received far less attention than text summarization. As the purpose of conversations is to exchange information between at least two interlocutors, key information about a certain topic is often scattered and spanned across multiple utterances and turns from different speakers. This phenomenon is more pronounced during spoken conversations, where speech characteristics such as backchanneling and false-starts might interrupt the topical flow. Moreover, topic diffusion and (intra-utterance) topic drift are also more common in human-to-human conversations. Such linguistic characteristics of dialogue topics make sentence-level extractive summarization approaches used in spoken documents ill-suited for summarizing conversations. Pointer-generator networks have effectively demonstrated its strength at integrating extractive and abstractive capabilities through neural modeling in text summarization. To the best of our knowledge, to date no one has adopted it for summarizing conversations. In this work, we propose a topic-aware architecture to exploit the inherent hierarchical structure in conversations to further adapt the pointer-generator model. Our approach significantly outperforms competitive baselines, achieves more efficient learning outcomes, and attains more robust performance.