China

Existing research assesses LLMs’ values by analyzing their stated inclinations, overlooking potential discrepancies between stated values and actions—termed the “Value-Action Gap.” This study introduces ValueActionLens, a framework to evaluate the alignment between LLMs’ stated values and their value-informed actions. The framework includes a dataset of 14.8k value-informed actions across 12 cultures and 11 social topics, along with two tasks measuring alignment through three metrics. Experiments show substantial misalignment between LLM-generated value statements and their actions, with significant variations across scenarios and models. Misalignments reveal potential harms, highlighting risks in relying solely on stated values to predict behavior. The findings stress the need for context-aware evaluations of LLM values and the value-action gaps.

EMNLP 2025

Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?

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.

Although preference optimization methods have improved reasoning performance in Large Language Models (LLMs), they often lack transparency regarding why one reasoning outcome is preferred over another. This limitation is especially critical in Automated Student Answer Scoring (ASAS), where explainability is essential to justify assessment outcomes. Verbal reinforcement learning offers the potential to generate explicit reflection, but it tends to produce superficial critiques that can harm assessment performance. Existing LLMs also struggle to reliably detect subtle reasoning errors in ASAS tasks. Moreover, manually identifying intermediate reasoning errors is expensive and difficult to scale. To address these challenges, we introduce a textbfcontrastive reflection synthesis pipeline that generates precise verbal feedback by identifying discrepancies in structure reasoning graph paths. Leveraging these synthetic reflection data, we propose textttDARS, a Dual-model Reflective Scoring framework featuring a dedicated Critic model trained for effective reflection. textttDARS achieves strong performance and consistently outperforms existing ASAS baselines across all evaluation metrics. Extensive experiments further provide novel insights into the value of reflection data, framework design, and the scaling behavior of textttDARS.

Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time

Chain-of-Thought (CoT) has been proven effective in enhancing the reasoning capabilities of large language models (LLMs). Recent advancements, such as OpenAI's o1 and DeepSeek-R1, suggest that scaling up the length of CoT sequences during inference could further boost LLM reasoning performance. However, due to the autoregressive nature of LLM decoding, longer CoT outputs lead to a linear increase in inference latency, adversely affecting user experience, particularly when the CoT exceeds 10,000 tokens. To address this limitation, we analyze the semantic importance of tokens within CoT outputs and reveal that their contributions to reasoning vary. Building on this insight, we propose TokenSkip, a simple yet effective approach that enables LLMs to selectively skip less important tokens, allowing for controllable CoT compression. Extensive experiments across various models and tasks demonstrate the effectiveness of TokenSkip in reducing CoT token usage while preserving strong reasoning performance. Notably, when applied to Qwen2.5-14B-Instruct, TokenSkip reduces reasoning tokens by 40% (from 313 to 181) on GSM8K, with less than a 0.4% performance drop.

TokenSkip: Controllable Chain-of-Thought Compression in LLMs

As large language models continue to grow in size, parameter-efficient fine-tuning (PEFT) has become increasingly crucial. While low-rank adaptation (LoRA) offers a solution through low-rank updates, its static rank allocation may yield suboptimal results. Adaptive low-rank adaptation (AdaLoRA) improves this with dynamic allocation but remains sensitive to initial and target rank configurations. We introduce AROMA, a framework that automatically constructs layer-specific updates by iteratively building up rank-one components with very few trainable parameters that gradually diminish to zero. Unlike existing methods that employ rank reduction mechanisms, AROMA introduces a dual-loop architecture for rank growth. The inner loop extracts information from each rank-one subspace, while the outer loop determines the number of rank-one subspaces, i.e., the optimal rank. We reset optimizer states to maintain subspace independence. AROMA significantly reduces parameters compared to LoRA and AdaLoRA while achieving superior performance on natural language understanding and commonsense reasoning tasks, offering new insights into adaptive PEFT.

AROMA: Autonomous Rank-one Matrix Adaptation

Previous research has primarily focused on the cognitive error detection capabilities of Large Language Models (LLMs), often prompting them to analyze mistakes in reasoning chains. However, few studies have examined the meta-cognitive abilities of LLMs (e.g., their self-awareness of step errors), which are crucial for their reliability. While studies on LLM self-evaluation present some measures, such as perplexity, which can reflect the answer correctness and be viewed as the lens of meta-cognition, they lack step-level analysis and adaptation. This paper studies the evaluation of LLM meta-cognition using the current lenses and how to improve these lenses. Specifically, we propose AutoMeco, an Automated Meta-cognition Evaluation framework for benchmarking the existing lenses. Furthermore, a training-free Markovian Intrinsic Reward Adjustment strategy, MIRA, is proposed to boost current meta-cognition lenses. Experimental results on three mathematical reasoning datasets and three LLMs show the reasonableness of AutoMeco by comparing it with Best-of-N verification. Moreover, the meta-cognition ability of LLMs can be better evaluated using MIRA.

Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens

Recently, large reasoning models have achieved impressive performance on various tasks by employing human-like deep thinking. However, the lengthy thinking process substantially increases inference overhead, making efficiency a critical bottleneck. In this work, we first demonstrate that \textit{NoThinking}, which prompts the reasoning model to skip thinking and directly generate the final solution, is a better choice for relatively simple tasks in terms of both performance and efficiency. Motivated by this, we propose \textit{AdaptThink}, a novel RL algorithm to teach reasoning models to choose the optimal thinking mode adaptively based on problem difficulty. Specifically, \textit{AdaptThink} features two core components: (1) a constrained optimization objective that encourages the model to choose \textit{NoThinking} while maintaining the overall performance; (2) an importance sampling strategy that balances \textit{Thinking} and \textit{NoThinking} samples during on-policy training, thereby enabling cold start and allowing the model to explore and exploit both thinking modes throughout the training process. Our experiments indicate that \textit{AdaptThink} significantly reduces the inference costs while further enhancing performance. Notably, on three math datasets, \textit{AdaptThink} reduces the average response length of DeepSeek-R1-Distill-Qwen-1.5B by 53% and improves its accuracy by 2.4%, highlighting the promise of adaptive thinking-mode selection for optimizing the balance between reasoning quality and efficiency.

AdaptThink: Reasoning Models Can Learn When to Think

Large Language Models (LLMs) require high quality preference datasets to align with human preferences. However, conventional methods for constructing such datasets face significant challenges: reliance on pre-collected instructions often leads to distribution mismatches with target models, while the need for sampling multiple stochastic responses introduces substantial computational overhead. In this work, we explore a paradigm shift by leveraging inherent regulation of LLMs' representation space for efficient and tailored preference dataset construction, named Icon². Specifically, it first extracts layer-wise direction vectors to encode sophisticated human preferences and then uses these vectors to filter self-synthesized instructions based on their inherent consistency. During decoding, bidirectional inherent control is applied to steer token representations, enabling the precise generation of response pairs with clear alignment distinctions. Experimental results demonstrate significant improvements in both alignment and efficiency. Llama3-8B and Qwen2-7B achieve an average win rate improvement of 13.89\% on AlpacaEval 2.0 and 13.45\% on Arena-Hard, while reducing computational costs by up to 48.1\%.

Icon²: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation

With the different roles that AI is expected to play in human life, imbuing large language models (LLMs) with different personalities has attracted increasing research interest. While the ``personification'' enhances human experiences of interactivity and adaptability of LLMs, it gives rise to critical concerns about content safety, particularly regarding bias, sentiment, and toxicity of LLM generation. This study explores how assigning different personality traits to LLMs affects the toxicity and biases of their outputs. Leveraging the widely accepted HEXACO personality framework developed in social psychology, we design experimentally sound prompts to test three LLMs' performance on three toxic and bias benchmarks. The findings demonstrate the sensitivity of all three models to HEXACO personality traits and, more importantly, a consistent variation in the biases, negative sentiment, and toxicity of their output. In particular, adjusting the levels of several personality traits can effectively reduce bias and toxicity in model performance, similar to humans' correlations between personality traits and toxic behaviors. The findings highlight the additional need to examine content safety besides the efficiency of training or fine-tuning methods for LLM personification, they also suggest a potential for the adjustment of personalities to be a simple and low-cost method to conduct controlled text generation.

Exploring the Impact of Personality Traits on LLM Toxicity and Bias

Deploying large language models (LLMs) for long-context inference remains challenging due to their substantial memory and computational demands. While techniques such as Key-Value (KV) cache compression are designed to reduce memory usage, they often neglect the structured sparsity inherent in the relationship between hidden states and their corresponding KV cache. In this work, we explore the role of uncertainty as a potential indicator of sparsity within LLMs. We propose UNComp, an uncertainty-aware framework that leverages truncated matrix entropy to identify areas of low information content, thereby revealing sparsity patterns that can be used for adaptive compression. Unlike traditional methods that apply uniform compression, UNComp dynamically adjusts its approach to compression, guided by uncertainty measures that reflect the importance of various model components. Our analysis shows that sparsity patterns, when derived from uncertainty estimates, can be exploited to reveal special long-range dependencies, such as retrieval heads and retrieval layers. This perspective not only enhances our understanding of how compression can be optimized but also provides new insights into the inherent sparsity of LLMs during long-context inference. By focusing on uncertainty to analyze the sparsity pattern in detail, UNComp reduces the KV cache size to 4.74% of the original, achieves a 6% prefill speedup, and improves throughput by 6.4× — not only delivering strong lossless compression performance, but also validating the effectiveness of the underlying theoretical tool. Our codes are submitted with the paper.

UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective

Large language models (LLMs) are commonly trained on multi-domain datasets, where domain sampling strategies significantly impact model performance due to varying domain importance across downstream tasks. Existing approaches for optimizing domain-level sampling strategies struggle with maintaining intra-domain consistency and accurately measuring domain impact. In this paper, we present Domain Impact-aware Data Sampling (DIDS). To ensure intra-domain consistency, a gradient clustering algorithm is proposed to group training data based on their learning effects, where a proxy language model and dimensionality reduction are employed to reduce computational overhead. To accurately measure domain impact, we develop a Fisher Information Matrix (FIM) guided metric that quantifies how domain-specific parameter updates affect the model's output distributions on downstream tasks, with theoretical guarantees. Furthermore, to determine optimal sampling ratios, DIDS combines both the FIM-guided domain impact assessment and loss learning trajectories that indicate domain-specific potential, while accounting for diminishing marginal returns. Extensive experiments demonstrate that DIDS achieves 3.4% higher average performance while maintaining comparable training efficiency. The code is available at https://anonymous.4open.science/r/DIDS.

DIDS: Domain Impact-aware Data Sampling for Large Language Model Training

Federated finetuning of Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) offers computational efficiency and preserves data privacy. However, applying LoRA in federated settings faces significant challenges: standard approaches struggle with data heterogeneity, and existing personalization techniques fail to precisely adapt shared global knowledge to individual client needs. To address these issues, we propose pFedGPT, a framework that leverages Hierarchical Bayesian Optimization (HBO) for fine-grained, personalized LoRA aggregation. pFedGPT intelligently partitions LoRA parameters based on model structure and client information, then employs HBO to hierarchically search for optimal, module-specific weights. This enables a nuanced integration of the downloaded global LoRA state with each client's local model, precisely capturing client-specific requirements. To manage the optimization cost inherent in HBO, pFedGPT incorporates efficient multi-fidelity evaluations and a curriculum learning strategy. Extensive experiments demonstrate that pFedGPT achieves state-of-the-art (SOTA) performance on personalized FL benchmarks, showcasing robustness and scalability while introducing only minimal (approx. 4%) additional optimization overhead. Our results also underscore the limitations of traditional FL methods for LoRA-based LLM personalization, highlighting the need for tailored approaches like pFedGPT.

Downloads

Next from EMNLP 2025

Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES