China

Large Language Models (LLMs) are highly sensitive to subtle, non-semantic variations in prompt phrasing and formatting. In this work, we present the first systematic evaluation of 4 methods for improving prompt robustness within a unified experimental framework. We benchmark these techniques on 8 models from Llama, Qwen and Gemma families across 52 tasks from Natural Instructions dataset. Our evaluation covers robustness methods from both fine-tuned and in-context learning paradigms, and tests their generalization against multiple types of distribution shifts. Finally, we extend our analysis to GPT-4.1 and DeepSeek V3 to assess frontier models&#39; current robustness to format perturbations. Our findings offer actionable insights into the relative effectiveness of these robustness methods, enabling practitioners to make informed decisions when aiming for stable and reliable LLM performance in real-world applications. Code: \urlstyle{tt}\url{https://anonymous.4open.science/r/prompt-instability-B6CD/}.

EMNLP 2025

When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

sensitivity

robustness

## Welcome to EMNLP 2022!
I am delighted to welcome you to EMNLP 2022! I believe this conference has been complicated beyond any precedent. Over the past year, it’s been thrilling to see the organization team approach each new puzzle with creativity and enthusiasm. We hope that those participating in Abu Dhabi as well as those joining remotely will leave the conference feeling newly inspired by the program and newly connected to our ever-growing community. Following EMNLP 2021 and major NLP conferences since, EMNLP 2022 is “hybrid,” serving both virtual and in-person participants.

Our key innovations for EMNLP 2022 include:

* EMNLP 2022 is “hybrid” in a second sense, as well: we allowed both direct and rolling review paper submissions, building on the pilot experiment of EMNLP 2021, which considered a small number of ARR submissions. 
* Familiar from NAACL but new to EMNLP, we’ve added an industry track.
* During the conference, “portals” will link virtual poster sessions to in-person conference participants during poster sessions each day.
* The first ACL-family conference in the United Arab Emirates.

 *Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA* 
***EMNLP 2022 General Chair***
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/a3db7a768409f05192210d98601edb25.png)](https://emnlp2022.rocket.chat/)

To access this site you need to register. Please register [here](https://2022.emnlp.org/registration/).

Register here

EMNLP 2022

Welcome!
EMNLP 2022 will take place in Abu Dhabi from December 7th to December 11th, 2022. And it will be held in hybrid mode, both online and offline.

Large Language Models (LLMs) are highly sensitive to subtle, non-semantic variations in prompt phrasing and formatting. In this work, we present the first systematic evaluation of 4 methods for improving prompt robustness within a unified experimental framework. We benchmark these techniques on 8 models from Llama, Qwen and Gemma families across 52 tasks from Natural Instructions dataset. Our evaluation covers robustness methods from both fine-tuned and in-context learning paradigms, and tests their generalization against multiple types of distribution shifts. Finally, we extend our analysis to GPT-4.1 and DeepSeek V3 to assess frontier models' current robustness to format perturbations. Our findings offer actionable insights into the relative effectiveness of these robustness methods, enabling practitioners to make informed decisions when aiming for stable and reliable LLM performance in real-world applications. Code: \urlstyle{tt}\url{https://anonymous.4open.science/r/prompt-instability-B6CD/}.

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." 

*Message from the General Chair, Dirk Hovy*

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

We present NarratEX, a dataset designed for the task of explaining the choice of the Dominant Narrative in a news article, and intended to support the research community in addressing challenges such as discourse polarization and propaganda detection. Our dataset comprises 1,056 news articles in four languages, Bulgarian, English, Portuguese, and Russian, covering two globally significant topics: the Ukraine-Russia War (URW) and Climate Change (CC). Each article is manually annotated with a dominant narrative and sub-narrative labels, and an explanation justifying the chosen labels. We describe the dataset, the process of its creation, and its characteristics. We present experiments with two new proposed tasks: Explaining Dominant Narrative based on Text, which involves writing a concise paragraph to justify the choice of the dominant narrative and sub-narrative of a given text, and Inferring Dominant Narrative from Explanation, which involves predicting the appropriate dominant narrative category based on an explanatory text. The proposed dataset is a valuable resource for advancing research on detecting and mitigating manipulative content, while promoting a deeper understanding of how narratives influence public discourse.

NarratEX Dataset: Explaining the Dominant Narratives in News Texts

Inference-time alignment enhances the performance of large language models without requiring additional training or fine-tuning but presents challenges due to balancing computational efficiency with high-quality output. Best-of-N (BoN) sampling, as a simple yet powerful approach, generates multiple responses and selects the best one, achieving improved performance but with a high computational cost. We propose TreeBoN, a novel framework that integrates a speculative tree-search strategy into Best-of-N (BoN) Sampling. TreeBoN maintains a set of parent nodes, iteratively branching and pruning low-quality responses, thereby reducing computational overhead while maintaining high output quality. Our approach also leverages token-level rewards from Direct Preference Optimization (DPO) to guide tree expansion and prune low-quality paths. We evaluate TreeBoN using AlpacaFarm, UltraFeedback, GSM8K, HH-RLHF, and TutorEval datasets, demonstrating consistent improvements. Specifically, TreeBoN achieves a 65% win rate at maximum lengths of 192 and 384 tokens, outperforming standard BoN with the same computational cost. Furthermore, TreeBoN achieves around a 60% win rate across longer responses, showcasing its scalability and alignment efficacy.

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling

Long-context extension seeks to expand the contextual window in pre-trained large language models (LLMs), allowing them to handle several multiples of their original training context lengths. The primary method for extending the window length involves expanding the initial positional encodings, such as interpolating and extrapolation new positions based on Rotary Position Embedding (RoPE). This expansion inevitably disrupts the positional encodings learned during pre-training, thereby affecting the attention allotment and introducing unseen positional encoding distributions. To address this issue, we propose a new extension strategy based on RoPE, namely Periodic Extrapolation Positional Encodings (PEPE). This strategy expands pre-trained high dimensional components of positional encodings by replicating them in a periodic manner, thereby neither altering the learned positional encoding spaces nor introducing new positional encoding distributions. Experiments demonstrate that PEPE-based approaches can significantly improve long-context extension capabilities using just one-fourth the fine-tuning steps required by state-of-the-art methods. In addition, we analyze the characteristics of PEPE based methods and the key parameters that contribute to their effectiveness. The code will be available publicly.

PEPE: Long-context Extension for Large Language Models via Periodic Extrapolation Positional Encodings

Jailbreak attacks, where harmful prompts bypass generative models' built-in safety, raise serious concerns about model vulnerability. While many defense methods have been proposed, the trade-offs between safety and helpfulness, and their application to Large Vision-Language Models (LVLMs), are not well understood. This paper systematically examines jailbreak defenses by reframing the standard generation task as a binary classification problem to assess model refusal tendencies for both harmful and benign queries. We identify two key defense mechanisms: \textit{safety shift}, which increases refusal rates across all queries, and \textit{harmfulness discrimination}, which improves the model's ability to differentiate between harmful and benign inputs. Using these mechanisms, we develop two ensemble defense strategies—inter-mechanism and intra-mechanism ensembles—to balance safety and helpfulness. Experiments on the MM-SafetyBench and MOSSBench datasets with LLaVA-1.5 models show that these strategies effectively improve model safety or optimize the trade-off between safety and helpfulness.

How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation

Large language models have demonstrated considerable capabilities in various mathematical tasks, yet they often fall short in rigorous, proof-based reasoning essential for research-level mathematics. Retrieval-augmented generation presents a promising direction for enhancing these capabilities. This paper systematically explores RAG for natural language theorem proving, revealing that LLMs, when augmented with retrieved proofs rather than just theorems, can function as potent mimetic theorem provers: these models can effectively generalize proof techniques found in unstructured retrieved contexts to construct correct proofs for novel theorems. Building upon this finding, we introduce Dual RAG, a simple yet effective RAG framework. Dual RAG employs LLMs to identify underlying reasoning challenges within theorems, augmenting both queries and document contexts to improve retrieval performance. Our experiments show that Dual RAG achieves substantial improvements in retrieval performance, with gains of up to 34.19%. Expert evaluations further confirm that these retrieval enhancements directly translate into higher quality proof generation. Notably, when integrated with the arXiv API, Dual RAG demonstrates the ability to prove research-level theorems in theoretical machine learning, highlighting its strong potential as a foundational element for a practical mathematical copilot.

Retrieval-Augmented Language Models are Mimetic Theorem Provers

Speculative decoding has emerged as a promising approach to accelerating large language model (LLM) generation using a fast drafter while maintaining alignment with the target model's distribution. However, existing approaches face a trade-off: external drafters offer flexibility but can suffer from slower drafting, while self-speculation methods use drafters tailored to the target model but require re-training. In this paper, we introduce novel drafters based on Mamba, a state-of-the-art state space model (SSM), as a solution that combines the best aspects of both approaches. By leveraging the linear structure of SSMs, our approach avoids the quadratic complexity inherent in traditional Transformer-based methods, enabling faster drafting and lower memory usage while maintaining the flexibility to work across different target models. We further enhance efficiency with a novel test-time tree search algorithm for generating high-quality draft candidates. Our empirical evaluation demonstrates that Mamba-based drafters not only outperform existing external drafting methods but are also comparable to state-of-the-art self-speculation approaches while using less memory and maintaining their cross-model adaptability.

Mamba Drafters for Speculative Decoding

Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe that these reasoning paths tend to include substantial redundancy; analyzing attention patterns reveals that attention scores are widely scattered, particularly incorrect answers exhibit greater attention sparsity. In this paper, we demonstrate that deliberately removing this redundancy in the reasoning process significantly improves the performance through clear thinking (i.e., removing distraction). Specifically, we systematically identify such redundancy by measuring token-level attention scores to a special end-of-thinking token, which is appended to an explicit instruction inserted to conclude each intermediate reasoning step. Furthermore, we propose structure-aware pruning that prioritizes removing tokens in low-contributing reasoning chunks over individual tokens. After evicting redundant tokens, we remove the injected end-of-thinking instruction, then resume the reasoning generation. We demonstrate that our method significantly improves the over all accuracy across reasoning-intensive benchmarks without any training involved. In particular, our method shows strong performance on challenging mathematics competition benchmarks such as AIME and AMC, where reasoning redundancy is more prevalent.

Think Clearly: Improving Reasoning via Redundant Token Pruning

Automated Claim Verification (CV), where claim's veracity is assessed against explicitly provided reference materials, is crucial in combating escalating online misinformation. This survey carefully analyzed 198 studies published between January 2022 and March 2025 to summarize recent work on corpus creation, system architectures, and the integration of large language models. We also conducted two case studies: the first looks at the relationship between claims and references. The second examines issues in claim decomposition. Our findings illuminate common corpus construction strategies and emerging trends in system architectures while highlighting remaining challenges in CV research.

A Systematic Survey of Claim Verification: Corpora, Systems, and Case Studies

In dialogue intent detection, the challenge of acquiring sufficient corpora and the high cost of manual annotation often lead to incorrectly labeled or unrepresentative samples, which can hinder the generalization ability of classification models. Additionally, as using large language models for generating synthetic samples for data augmentation becomes more common, these synthetic samples may exacerbate the problem by introducing additional noise due to the models’ limited prior knowledge. To address this challenge, this paper proposes an interpretable Sample Filter by Topic Modeling (SFTM) framework. By evaluating the diversity and authenticity of the samples, SFTM effectively reduces the quantity of real and synthetic samples while improving the performance of the classification models.

From Noise to Clarity: Filtering Real and LLM-Generated Samples for Enhanced Intent Detection

The advancement of large language models (LLMs) has enabled the construction of multi-agent systems to solve complex tasks by dividing responsibilities among specialized agents, such as a planning agent for subgoal generation and a grounding agent for executing tool-use actions. Most existing methods typically fine-tune these agents independently, leading to capability gaps among them with poor coordination. To address this, we propose MOAT, a Multi-Agent Joint Alignment Tuning framework that improves agents collaboration through iterative alignment. MOAT alternates between two key stages: (1) Planning Agent Alignment, which optimizes the planning agent to generate subgoal sequences that better guide the grounding agent; and (2) Grounding Agent Improving, which fine-tunes the grounding agent using diverse subgoal-action pairs generated by the agent itself to enhance its generalization capablity. Theoretical analysis proves that MOAT ensures a non-decreasing and progressively convergent training process. Experiments across six benchmarks demonstrate that MOAT outperforms state-of-the-art baselines, achieving average improvements of 3.1% on held-in tasks and 4.4% on held-out tasks.

Downloads

Next from EMNLP 2025

NarratEX Dataset: Explaining the Dominant Narratives in News Texts

Similar lecture

Exploring The Landscape of Distributional Robustness for Question Answering Models