China

Large language models (LLMs) demonstrate remarkable performance across diverse tasks, yet their effectiveness frequently depends on costly commercial APIs or cloud services. Model selection thus entails a critical trade-off between performance and cost: high-performing LLMs typically incur substantial expenses, whereas budget-friendly small language models (SLMs) are constrained by limited capabilities. Current research primarily proposes two routing strategies: pre-generation routing and cascade routing. Both approaches have distinct characteristics, with cascade routing typically offering superior cost-effectiveness and accuracy despite its higher latency. To further address the limitations of both approaches, we introduce SATER, a dual-mode compatible approach that fine-tunes models through shortest-response preference optimization and a confidence-aware rejection mechanism. SATER significantly reduces redundant outputs and response times, while improving both the performance of pre-generation routing and the efficiency of cascade routing. Experiments across three SLMs and six datasets, varying in type and complexity, demonstrate that SATER achieves comparable performance while consistently reducing computational costs by over 50\% and cascade latency by over 80\%.

EMNLP 2025

SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading

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*

[**Link to Conference Handbook**](https://drive.google.com/file/d/1johU5QqVVYO4RfH7QcIORr7qrVBdzdwC/view?usp=sharing)





<br>

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

We present CIFLEX (Contextual Instruction FLow with EXecution), a novel execution system for efficient sub-task handling in multi-turn interactions with a single on-device large language model (LLM). As LLMs become increasingly capable, a single model is expected to handle diverse sub-tasks that more effectively and comprehensively support answering user requests. Naive approach reprocesses the entire conversation context when switching between main and sub-tasks (e.g., query rewriting, summarization), incurring significant computational overhead. CIFLEX mitigates this overhead by reusing the key-value (KV) cache from the main task and injecting only task-specific instructions into isolated side paths. After sub-task execution, the model rolls back to the main path via cached context, thereby avoiding redundant prefill computation. To support sub-task selection, we also develop a hierarchical classification strategy tailored for small-scale models, decomposing multi-choice decisions into binary ones. Experiments show that CIFLEX significantly reduces computational costs without degrading task performance, enabling scalable and efficient multi-task dialogue on-device.

CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM

With the growing computational demands of large language models (LLMs), efficient inference has become increasingly critical for practical deployment. Depth pruning has emerged as a promising approach for reducing the computational costs of large language models by removing transformer layers. However, existing methods typically rely on fixed block masks, which can lead to suboptimal performance across different tasks and inputs. In this paper, we propose IG-Pruning, a novel input-aware block-wise pruning method that dynamically selects layer masks at inference time. Our approach consists of two stages: (1) Discovering diverse mask candidates through semantic clustering and L0 optimization, and (2) Implementing efficient dynamic pruning without the need for extensive training. Experimental results demonstrate that our method consistently outperforms state-of-the-art static depth pruning methods, making it particularly suitable for resource-constrained deployment scenarios.

IG-Pruning: Input-Guided Block Pruning for Large Language Models

Theory-of-Mind (ToM) tasks pose a unique challenge for small language models (SLMs) with limited scale, which often lack the capacity to perform deep social reasoning. In this work, we propose DEL-ToM, a framework that improves ToM reasoning through inference-time scaling rather than architectural changes. Our approach decomposes ToM tasks into a sequence of belief updates grounded in Dynamic Epistemic Logic (DEL), enabling structured and transparent reasoning. We train a verifier, called the Process Belief Model (PBM), to score each belief update step using labels generated automatically via a DEL simulator. During inference, candidate belief traces generated by a language model are evaluated by the PBM, and the highest-scoring trace is selected. This allows SLMs to emulate more deliberate reasoning by allocating additional compute at test time. Experiments across multiple model scales and benchmarks show that DEL-ToM consistently improves performance, demonstrating that verifiable belief supervision can significantly enhance ToM abilities of SLMs without retraining.

DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic

Large language models (LLMs) often succumb to users' viewpoints when faced with conflicting perspectives. We identify two key biases underlying this issue : stance homogeneity bias and human preference bias. To address these biases, we propose a novel two-stage training framework: Multi-stance Discussion Sampling and Truth Alignment Training (MDTA). First, we introduce an equal multi-stance discussion framework to automatically generate multi-model discussion datasets. Based on this framework, we construct the first and largest multi-model fair discussion dataset named Eq-Discussion for supervised fine-tuning, reducing stance homogeneity bias. Second, we optimize Reinforcement Learning from Human Feedback (RLHF) to align with discussion correctness, mitigating human preference bias. Extensive experimental results demonstrate that MDTA effectively reduces both biases and significantly enhances the performance of LLMs across a variety of downstream tasks, including reading comprehension, logical reasoning, and social question answering. Furthermore, we observe that MDTA improves the generalization capabilities of LLMs, leading to substantial performance improvements in non-discussion scenarios and on out-of-domain datasets.

Stimulate the Critical Thinking of LLMs via Debiasing Discussion

There has been a surge in the use of large language models (LLM) conversational agents to generate responses based on long-term history from multiple sessions. However, existing long-term open-domain dialogue datasets lack complex, real-world personalization and fail to capture implicit reasoning—where relevant information is embedded in subtle, syntactic, or semantically distant connections rather than explicit statements. In such cases, traditional retrieval methods fail to capture relevant context, and long-context modeling also becomes inefficient due to numerous complicated persona-related details. To address this gap, we introduce ImplexConv, a large-scale long-term dataset with 2,500 examples, each containing approximately 100 conversation sessions, designed to study implicit reasoning in personalized dialogues. Additionally, we propose TaciTree, a novel hierarchical tree framework that structures conversation history into multiple levels of summarization. Instead of brute-force searching all data, TaciTree enables an efficient, level-based retrieval process where models refine their search by progressively selecting relevant details. Our experiments demonstrate that TaciTree significantly improves the ability of LLMs to reason over long-term conversations with implicit contextual dependencies.

Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning

To assist users in complex tasks, LLMs generate plans: step-by-step instructions towards a goal. While alignment methods aim to ensure LLM plans are helpful, they train (RLHF) or evaluate (ChatbotArena) on what users prefer, assuming this reflects what helps them. We test this with Planorama: an interface where 126 users answer 300 multi-step questions with LLM plans. We get 4388 plan executions and 5584 comparisons to measure plan helpfulness (QA success) and user preferences on plans, and recreate the setup in agents and reward models to see if they simulate or prefer what helps users. We expose: 1) user/model preferences and agent success do not accurately predict which plans help users, so common alignment feedback can misalign with helpfulness; 2) this gap is not due to user-specific preferences, as users are similarly successful when using plans they prefer/disprefer; 3) surface-level cues like brevity and question similarity strongly link to preferences, but such biases fail to predict helpfulness. In all, we argue aligning helpful LLMs needs feedback from real user interactions—not just preferences of what looks helpful—so we discuss the plan NLP researchers can execute to solve this problem.

A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users

Chain-of-thought (CoT) distillation allows a large language model (LLM) to guide a small language model (SLM) in reasoning tasks. Existing methods train the SLM to learn the long rationale in one iteration, resulting in two issues: 1) Long rationales lead to a large token-level batch size during training, making gradients of core reasoning tokens (i.e., the token will directly affect the correctness of subsequent reasoning) over-smoothed as they contribute a tiny fraction of the rationale. As a result, the SLM converges to sharp minima where it fails to grasp the reasoning logic. 2) The response is slow, as the SLM must generate a long rationale before reaching the answer. Therefore, we propose chunk-wise training (CWT), which uses a heuristic search to divide the rationale into internal semantically coherent chunks and focuses SLM on learning from only one chunk per iteration. In this way, CWT naturally isolates non-reasoning chunks that do not involve the core reasoning token (e.g., summary and transitional chunks) from the SLM learning for reasoning chunks, making the fraction of the core reasoning token increase in the corresponding iteration. Based on CWT, skip-thinking training (STT) is proposed. STT makes the SLM automatically skip non-reasoning medium chunks to reach the answer, improving reasoning speed while maintaining accuracy. We validate our approach on a variety of SLMs and multiple reasoning tasks.

Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster

Large language models (LLMs) are widely deployed as zero-shot evaluators for answer grading, content moderation, and document ranking. Yet studies show that guard models (Guards)—LLMs fine-tuned for safety—remain vulnerable to "jailbreak" attacks, jeopardising downstream chatbots. We confirm this weakness on three public benchmarks (BeaverTails, XSTest, AdvBench) and trace it to representation shifts that arise in the embedding layer and cascade through the Transformer stack. To counteract the effect, we introduce Gamma-Guard: lightweight residual adapters inserted after the embeddings and at sparse intervals in the model. The adapters start with zero-scaled gates, so they retain the original behaviour; a brief adversarial fine-tuning phase then teaches them to denoise embeddings and refocus attention. With fewer than 0.1% extra parameters and only a 2% latency increase, Gamma-Guard lifts adversarial accuracy from <5% to 95% a 90 percentage-point gain while reducing clean-data accuracy by just 8 percentage points. Extensive ablations further show that robustness improvements persist across different layer placements and model sizes. To our knowledge, this is the first approach that directly augments large Guards with trainable adapters, providing a practical path toward safer large-scale LLM deployments.

Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Models

Chain-of-Thought (CoT) reasoning improves performance on complex tasks but introduces significant inference latency due to its verbosity. In this work, we propose Multiround Adaptive Chain-of-Thought Compression (\textbf{MACC}), a framework that leverages the \textit{token elasticity phenomenon}—where overly small token budgets may paradoxically increase output length—to progressively compress CoTs via multiround refinement. This adaptive strategy allows MACC to dynamically determine the optimal compression depth for each input. Our method achieves an average accuracy improvement of 5.6% over state-of-the-art baselines, while also reducing CoT length by an average of 47 tokens and significantly lowering latency. Furthermore, we show that \textbf{test-time performance}—accuracy and token length—can be reliably predicted using interpretable features like perplexity and compression rate \textbf{on training set}. Evaluated across different models, our method enables efficient model selection and forecasting without repeated fine-tuning, demonstrating that CoT compression is both effective and predictable. Our code will be released to facilitate reproducibility and future research in CoT compression.

From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement

Rapid LLM advancements heighten fake news risks by enabling the automatic generation of increasingly sophisticated misinformation. Previous detection methods, including fine-tuned small models or LLM-based detectors, often struggle with its dynamically evolving nature. In this work, we propose a novel framework called the Symbolic Adversarial Learning Framework (SALF), which implements an adversarial training paradigm by an agent symbolic learning optimization process, rather than relying on numerical updates. SALF introduces a paradigm where the generation agent crafts deceptive narratives, and the detection agent uses structured debates to identify logical and factual flaws for detection, and they iteratively refine themselves through such adversarial interactions. Unlike traditional neural updates, we represent agents using agent symbolic learning, where learnable weights are defined by agent prompts, and simulate back-propagation and gradient descent by operating on natural language representations of weights, loss, and gradients. Experiments on two multilingual benchmark datasets demonstrate SALF's effectiveness, showing it generates sophisticated fake news that degrades state-of-the-art detection performance by up to 53.4% in Chinese and 34.2% in English on average. SALF also refines detectors, improving detection of refined content by up to 7.7%. We hope our work inspires further exploration into more robust, adaptable fake news detection systems.

Downloads

Next from EMNLP 2025

CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES