China

While Large Language Model-based agents have demonstrated substantial progress in task completion, existing evaluation benchmarks tend to overemphasize single-task performance, with insufficient attention given to the crucial aspects of multitask planning and execution efficiency required in real-world scenarios. To bridge this gap, we present Recipe2Plan, a novel benchmark framework based on real-world cooking scenarios. Unlike conventional benchmarks, Recipe2Plan challenges agents to optimize cooking time through parallel task execution while respecting temporal constraints i.e. specific actions need to be performed within a particular time interval following the preceding steps. Overly aggressive local parallelization may disrupt this constraint, potentially compromising the entire cooking process. This strict time constraint between actions raises a unique challenge for agents to balance between maximizing concurrent operations and adhering to critical timing constraints. Extensive experiments with state-of-the-art models reveal challenges in maintaining this balance between efficiency and feasibility. The results highlight the need for improved temporal awareness and global multitasking capabilities in large language models. We will open-source our benchmark and code.

EMNLP 2025

Recipe2Plan: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actions

planning

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

poster

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community."<br>

*Message from the General Chair, Dirk Hovy*





<br>

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Retrieval-Augmented Generation (RAG) systems are widely adopted in knowledge-intensive NLP tasks, but current evaluations often overlook the structural complexity and multi-step reasoning required in real-world scenarios. These benchmarks overlook key factors such as the interaction between retrieval difficulty and reasoning depth. To address this gap, we propose GRADE, a novel evaluation framework that models task difficulty along two orthogonal dimensions: (1) reasoning depth, defined by the number of inference steps (hops), and (2) semantic distance between the query and its supporting evidence. We construct a synthetic multi-hop QA dataset from factual news articles by extracting knowledge graphs and augmenting them through semantic clustering to recover missing links, allowing us to generate diverse and difficulty-controlled queries. Central to our framework is a 2D difficulty matrix that combines generator-side and retriever-side difficulty. Experiments across multiple domains and models show that error rates strongly correlate with our difficulty measures, validating their diagnostic utility. GRADE enables fine-grained analysis of RAG performance and provides a scalable foundation for evaluating and improving multi-hop reasoning in real-world applications.

GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG Evaluation

Large language models (LLMs) face persistent challenges when handling long-context tasks, most notably the \textit{“lost in the middle”} issue, where information located in the middle of a long input tends to be underutilized. Some existing methods that reduce input have the risk of discarding key information, while others that extend context windows often lead to attention dispersion. To address these limitations, we propose \textit{Tree of Agents (TOA)}, a multi-agent reasoning framework that segments the input into chunks processed by independent agents. Each agent generates its local cognition, then agents dynamically exchange information for collaborative reasoning along tree-structured paths. TOA enables agents to probe different reasoning orders for multi-perspective understanding, effectively mitigating position bias and reducing hallucinations. To improve processing efficiency, we incorporate prefix-hash caching and adaptive pruning strategies, achieving significant performance improvements with comparable API overhead. Experiments show that TOA, powered by compact LLaMA3.1-8B, significantly outperforms multiple baselines and demonstrates comparable performance to the latest and much larger commercial models, such as Gemini1.5-pro, on various long-context tasks. Code is available at \url{https://anonymous.4open.science/r/Tree-of-Agents-4C9B/

Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning

In this paper, we introduce a new \emph{process prejudge} strategy in LLM reasoning to demonstrate that bootstrapping with process prejudge allows the LLM to adaptively anticipate the errors encountered when advancing the subsequent reasoning steps, similar to people sometimes pausing to think about what mistakes may occur and how to avoid them, rather than relying solely on trial and error. Specifically, we define a prejudge node in the rationale, which represents a reasoning step, with at least one step that follows the prejudge node that has no paths toward the correct answer. To synthesize the prejudge reasoning process, we present an automated reasoning framework with a dynamic tree-searching strategy. This framework requires only one LLM to perform answer judging, response critiquing, prejudge generation, and thought completion. Furthermore, we develop a two-phase training mechanism with supervised fine-tuning (SFT) and reinforcement learning (RL) to further enhance the reasoning capabilities of LLMs. Experimental results from competition-level complex reasoning demonstrate that our method can teach the model to prejudge before thinking and significantly enhance the reasoning ability of LLMs~\footnote{Code and data is released at \url{https://github.com/xxx}.}.

Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning

Large language models (LLMs) offer a novel and convenient avenue for humans to acquire knowledge. However, LLMs are prone to providing "midguy" answers regardless of users' knowledge background, thereby failing to meet each user's personalized needs. To tackle the problem, we propose to generate personalized answers with LLMs based on users' past question-answering records. We dynamically generate and update a user's domain and global profiles as the user asks questions, and use the latest profile as the context to generate the answer for a newly-asked question. To save tokens, we propose to compress the domain profile into a set of keywords and use the keywords to prompt LLMs. We theoretically analyze the effectiveness of the compression strategy. Experimental results show that our method can generate more personalized answers than comparative methods. The code and dataset are available at https://anonymous.4open.science/r/PRF-QA-169B.

Personalized Question Answering with User Profile Generation and Compression

Typically, parametric adaptation methods such as domain-adaptive pretraining (DAP) and retrieval-augmented generation (RAG) have been considered effective approaches for adapting large language models (LLMs) to new knowledge or domains. To unify positive effects of parametric adaptation and RAG, this paper proposes GenPoE, i.e., "generative" passage-level mixture of experts (MoEs) for enhancing knowledge of LLMs. The key component is its novel MoE-generating hypernetwork which takes in-context retrieved passages and generates their "expert’’ parameters, where these generated parameters are then integrated into LLMs by forming expert networks. With its use of "generated" parameters, GenPoE does not require a separate parameter training or finetuning stage, which is often costly. By parameterizing passages into expert networks, GenPoE likely exhibits robustness even when the retrieved passages are irrelevant. Experiment results in two open-domain question answering (QA) tasks present that GenPoE shows improved performances over other passage-level knowledge editing, and its combination of RAG produces superior performances over RAG. Our data and code will be available at \url{https://github.com/XXX/XXX}.

GenPoE: Generative Passage-level Mixture of Experts for Knowledge Enhancement of LLMs

Retrieval-augmented generation (RAG) has become a fundamental paradigm for addressing the challenges faced by large language models in handling real-time information and domain-specific problems. Traditional RAG systems primarily rely on the in-context learning (ICL) capabilities of the large language model itself. Still, in-depth research on the specific capabilities needed by the RAG generation model is lacking, leading to challenges with inconsistent document quality and retrieval system imperfections. Even the limited studies that fine-tune RAG generative models often lack a granular focus on RAG tasks or a deeper utilization of chain-of-thought processes. To address this, we propose that RAG models should possess three progressively hierarchical abilities (1) Filtering: the ability to select relevant information; (2) Combination: the ability to combine semantic information across paragraphs; and (3) RAG-specific reasoning: the ability to further process external knowledge using internal knowledge. Thus, we introduce our new RAG instruction fine-tuning method, Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation (HIRAG) incorporates a "think before answering" strategy. This method enhances the model's open-book examination capability by utilizing multi-level progressive chain-of-thought. Experiments show that the HIRAG training strategy significantly improves the model's performance on datasets such as RGB, PopQA, MuSiQue, HotpotQA, and PubmedQA.

HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation

Web agents powered by Large Language Models (LLMs) show promise for next-generation AI, but their limited reasoning in uncertain, dynamic web environments hinders robust deployment. In this paper, we identify key reasoning skills essential for effective web agents, i.e., reflection & lookahead, branching, and rollback, and curate trajectory data that exemplifies these abilities by reconstructing the agent's (inference-time) reasoning algorithms into chain-of-thought rationales. We conduct experiments in the agent self-improving benchmark, OpenWebVoyager, and demonstrate that distilling salient reasoning patterns into the backbone LLM via simple fine-tuning can substantially enhance its performance. Our approach yields significant improvements across multiple benchmarks, including WebVoyager, Mind2web-live, and SimpleQA (web search), highlighting the potential of targeted reasoning skill enhancement for web agents.

WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback

Large reasoning models (LRMs) excel at solving complex tasks by leveraging long chain-of-thought (CoT) reasoning. However, this often leads to overthinking on simple tasks, resulting in unnecessary computational overhead. We observe that LRMs inherently possess the capability for efficient short CoT reasoning, which can be reliably elicited through prompt design. To leverage this capability, we propose ThinkSwitcher, a framework that enables a single LRM to dynamically switch between short and long CoT modes based on task complexity. ThinkSwitcher introduces a lightweight switching module trained with supervision signals derived from the relative performance of each reasoning mode across tasks. Experiments on multiple reasoning benchmarks show that ThinkSwitcher reduces computational cost by 20-30% while maintaining high accuracy on complex tasks. This demonstrates the effectiveness of ThinkSwitcher as a scalable and efficient solution for unified LRM deployment.

ThinkSwitcher: When to Think Hard, When to Think Fast

In competitive programming task, problem statements are often embedded within elaborate narrative backgrounds, requiring deep understanding of the underlying solutions to successfully complete the tasks. Current code generation models primarily focus on token-level semantic modeling, highly susceptible to distractions from irrelevant narrative statements. Inspired by RAG, retrieving reference code with similar solutions may help enhance model performance on difficult problems. However, existing retrieval models also emphasize surface-level semantic similarity, neglecting the deeper solution-level logical similarities that are critical in competitive programming. Therefore, designing ranking models capable of accurately identifying and retrieving problems and corresponding codes remains an urgent research problem in competitive code generation. In this paper, we propose SolveRank, a solution-aware ranking model empowered by synthetic data for competitive programming tasks. Specifically, we leverage the DeepSeek-R1 model to generate logically equivalent but differently phrased new problems, verified by GPT-4o for solution consistency. Then, we train SolveRank with these as positive samples and BM25/random-retrieved problems as negatives. During inference, SolveRank retrieves relevant problems and corresponding code from the corpus to assist a downstream code generator. Experiments on the xCodeEval dataset demonstrate that SolveRank outperforms SOTA ranking methods in precision and recall metrics, and boosts code generation performance for difficult problems.

Beyond the Surface: A Solution-Aware Retrieval Model for Competition-level Code Generation

Recent advancements of general domain oriented Role-playing Agents (RPAs) have enabled the agents to maintain character properties in a wide spectrum of daily tasks beyond mere scenario based chit-chatting. Nonetheless, current works lacks consideration of replicating internal properties of characters like fine-grained memories, and failed to take account of aligning with the knowledge boundary of each character, resulting in degraded personalization and proneness to character hallucination in general domain. To address these problems, we draw inspirations from the context effect theory and propose a retrieval-based framework TailorRPA to harvest tailored general domain instructions to improve integration of fine-grained memories and incorporate general-domain protective queries to help shape the character-wise knowledge boundary, alleviating character hallucination. Based on the framework, we developed a role-playing dataset TailorGen, comprising both role-specific and general-domain instructions. Through empirical experiments, we proved the superiority of TailorRPA in eliciting general domain role-playing capabilities and alleviating character hallucination compared to baseline methods, and explored the existence of character hallucination in state-of-the-art proprietary models through empirical experiments, underlining the importance of our work.

Downloads

Next from EMNLP 2025

GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG Evaluation

Similar lecture

Aligning Actions Across Recipe Graphs

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES