China

Recent advances in reasoning with large language models (LLMs) have popularized Long Chain-of-Thought (LCoT), a strategy that encourages deliberate and step-by-step reasoning before producing a final answer. While LCoTs have enabled expert-level performance in complex tasks, how the internal structures of their reasoning chains drive, or even predict, the correctness of final answers remains a critical yet underexplored question. In this work, we present LCoT2Tree, an automated framework that converts sequential LCoTs into hierarchical tree structures and thus enables deeper structural analysis of LLM reasoning. Using graph neural networks (GNNs), we reveal that structural patterns extracted by LCoT2Tree, including exploration, backtracking, and verification, serve as stronger predictors of final performance across a wide range of tasks and models. Leveraging an explainability technique, we further identify critical thought patterns such as over-branching that account for failures. Beyond diagnostic insights, the structural patterns by LCoT2Tree support practical applications, including improving Best-of-N decoding effectiveness. Overall, our results underscore the critical role of internal structures of reasoning chains, positioning LCoT2Tree as a powerful tool for diagnosing, interpreting, and improving reasoning in LLMs.

EMNLP 2025

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning

cognitive behavior

long chain-of-thought

reasoning

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

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.

Existing parameter-efficient fine-tuning (PEFT) methods for large language models (LLMs), such as LoRA and PiSSA, constrain model updates to low-rank subspaces, limiting their expressiveness and leading to suboptimal performance on complex tasks. To address this, we introduce **H**igh-rank **D**istributed **PiSSA (HD-PiSSA)**, a distributed PEFT approach that initializes **orthogonal adapters** across different devices and aggregates their delta updates collectively on (W) for fine-tuning. Unlike Data Parallel LoRA or PiSSA, which maintain identical adapters across all devices, HD-PiSSA assigns different principal components of the pre-trained weights to each GPU, significantly expanding the range of update directions. This results in over 16× higher effective updated ranks than data-parallel LoRA or PiSSA when fine-tuning on 8 GPUs with the same per-device adapter rank. Empirically, HD-PiSSA benefits from this extra optimization flexibility and outperforms both LoRA and PiSSA across a variety of challenging downstream tasks, including mathematics, code, and multi-task learning.

HD-PiSSA: High-Rank Distributed Orthogonal Adaptation

There is an emerging effort to develop NLP for Indonesia’s 700+ local languages, but progress remains costly due to the need for direct engagement with native speakers. However, it is unclear what these language communities truly need from language technology. To address this, we conduct a nationwide survey to assess the actual needs of native speakers in Indonesia. Our findings indicate that addressing language barriers—particularly through machine translation and information retrieval—is the most critical priority. Although there is strong enthusiasm for advancements in language technology, concerns around privacy, bias, and the use of public data for AI training highlight the need for greater transparency and clear communication to support broader AI adoption.

What Do Indonesians Really Need from Language Technology? A Nationwide Survey

High-quality datasets are essential for building effective task-oriented dialogue (TOD) systems. The existing TOD datasets often present overly simplified interactions, where users incrementally express straightforward requests that can be managed with basic slot-value style dialogue states, such as “hotel-area = east.” However, this approach does not reflect real-life scenarios in which users may express complex constraints and preferences. To address this gap, in this paper, we propose SQLWOZ, a novel TOD dataset designed to capture complex, real-world user requirements. The user requirements in SQLWOZ include the four categories: 1) multiple values for a slot, 2) excluded values within a slot, 3) preferred or prioritized values, and 4) conditional values based on other conditions. We utilize SQL statements as a formalized and expressive representation of dialogue states within SQLWOZ. To evaluate the dataset, we adapt large language models as dialogue agents and conduct extensive experiments on the SQL-based dialogue state tracking, dialogue response generation and end-to-end TOD tasks. The experimental results demonstrate the complexity and quality of SQLWOZ, establishing it as a new benchmark for advancing TOD research.

SQLWOZ: A Realistic Task-Oriented Dialogue Dataset with SQL-Based Dialogue State Representation for Complex User Requirements

Large language models (LLMs) are increasingly used in social science simulations. While their performance on reasoning and optimization tasks has been extensively evaluated, less attention has been paid to their ability to simulate the variability and adaptability of human decision-making. We propose a process-oriented evaluation framework with progressive interventions (Intrinsicality, Instruction, and Imitation) to examine how LLM agents adapt under different levels of external guidance and human-derived noise. We validate the framework on two classic economics tasks: irrationality in the second-price auction and decision bias in the newsvendor problem, demonstrating behavior gaps between LLMs and humans. We find that LLMs, by default, converge on stable and conservative strategies that diverge from observed human behaviors. Risk-framed instructions impact LLM behavior predictably but do not replicate human-like diversity. Incorporating human data through in-context learning narrows the gap but fails to capture the strategic variability of human subjects. These results highlight a persistent alignment gap in behavioral fidelity, suggesting that future LLM evaluations should consider more process-level realism. We present a process-oriented approach for assessing LLMs in dynamic decision-making tasks, offering guidance for their responsible application in synthetic data generation and social science research.

Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Making

Although small Large Language models (sLLMs) have been widely deployed in practical applications, little attention has been paid to their value-reasoning abilities, particularly in terms of reasoning reliability. To address this gap, we propose a systematic evaluation framework for assessing the Value-Reasoning Reliability of sLLMs. We define Value-Reasoning Reliability as comprising: (1) Output consistency under identical prompts, (2) Output Robustness under semantically equivalent prompts, (3) Maintaining stable value reasoning in the face of attacks, and (4) Consistency of value reasoning in open-ended value expression tasks. Our framework includes three core tasks: Repetition Consistency task, Interaction Stability task, and Open-ended Expression Consistency task. We further incorporate self-reported confidence scores to evaluate the model’s value reasoning reliability from two perspectives: the model’s self-awareness of its values, and its value-based decision-making. Our findings show that models vary significantly in their stability when responding to value-related questions. Moreover, we observe considerable output randomness, which is not always correlated with the self-reported confidence or expressed value preferences. This suggests that current models lack a reliable internal mechanism for stable value reasoning when addressing value-sensitive queries.

Investigating Value-Reasoning Reliability in Small Large Language Models

Explanations are an important tool for gaining insights into model behavior, calibrating user trust, and ensuring compliance. Past few years have seen a flurry of methods for generating explanations, many of which involve computing model gradients or solving specially designed optimization problems. Owing to the remarkable reasoning abilities of LLMs, *self-explanation*, ie, prompting the model to explain its outputs has recently emerged as a new paradigm. We study a specific type of self-explanations, *self-generated counterfactual explanations* (SCEs). We design tests for measuring the efficacy of LLMs in generating SCEs. Analysis over various LLM families, sizes, temperatures, and datasets reveals that LLMs often struggle to generate SCEs. When they do, their prediction often does not agree with their own counterfactual reasoning.

Can LLMs Explain Themselves Counterfactually?

Large Language Models (LLMs) have become indispensable tools across various applications, making it more important than ever to ensure the quality and the trustworthiness of their outputs. This has led to growing interest in uncertainty quantification (UQ) methods for assessing the reliability of LLM outputs. Many existing UQ techniques rely on token probabilities, which inadvertently introduces a bias with respect to the length of the output. While some methods attempt to account for this, we demonstrate that such biases persist even in length-normalized approaches. To address the problem, here we propose UNCERTAINTY-LINE (Length-INvariant Estimation), a simple debiasing procedure that regresses uncertainty scores on output length and uses the residuals as corrected, length-invariant estimates. Our method is post-hoc, model-agnostic, and applicable to a range of UQ measures. Through extensive evaluation on machine translation, summarization, and question-answering tasks, we demonstrate that UNCERTAINTY-LINE consistently improves over even nominally length-normalized UQ methods uncertainty estimates across multiple metrics and models.

UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Models

Large language models (LLMs) are increasingly used for zero-shot conversation summarization, but often exhibit positional bias—tending to overemphasize content from the beginning or end of a conversation while neglecting the middle. To address this issue, we introduce PoSum-Bench, a comprehensive benchmark for evaluating positional bias in conversational summarization, featuring diverse English and French conversational datasets spanning formal meetings, casual conversations, and customer service interactions. We propose a novel semantic similarity-based sentence-level metric to quantify the direction and magnitude of positional bias in model-generated summaries, enabling systematic and reference-free evaluation across conversation positions, languages, and conversational contexts. Our benchmark and methodology thus provide the first systematic, cross-lingual framework for reference-free evaluation of positional bias in conversational summarization, laying the groundwork for developing more balanced and unbiased summarization models.

PoSum-Bench: Benchmarking Position Bias in LLM-based Conversational Summarization

Dialects represent a significant component of human culture and are found across all regions of the world. In Germany, more than 40% of the population speaks a regional dialect (Adler and Hansen, 2022). However, despite cultural importance, individuals speaking dialects often face negative societal stereotypes. We examine whether such stereotypes are mirrored by large language models (LLMs). We draw on the sociolinguistic literature on dialect perception to analyze traits commonly associated with dialect speakers. Based on these traits, we assess the dialect naming bias and dialect usage bias expressed by LLMs in two tasks: association task and decision task. To assess a model’s dialect usage bias, we construct a novel evaluation corpus that pairs sentences from seven regional German dialects (e.g., Alemannic and Bavarian) with their standard German counterparts. We find that: (1) in the association task, all evaluated LLMs exhibit significant dialect naming and dialect usage bias against German dialect speakers, reflected in negative adjective associations; (2) all models reproduce these dialect naming and dialect usage biases in their decision making; and (3) contrary to prior work showing minimal bias with explicit demographic mentions, we find that explicitly labeling linguistic demographics—German dialect speakers—amplifies bias more than implicit cues like dialect usage.

Large Language Models Discriminate Against Speakers of German Dialects

Attention-based language models typically rely on the softmax function to convert attention logits into probability distributions. However, this mechanism can lead to *attention entropy collapse*, where attention is focused on a single token, causing training instability. In this work, we identify the high *variance sensitivity* of softmax as a primary cause of this collapse. We show that *entropy-stable* attention mechanisms, which either control or are insensitive to the variance of attention logits, can prevent entropy collapse and enable more stable training. We provide empirical evidence of this effect in both large language models (LLMs) and a small Transformer model composed solely of self-attention and support our findings with theoretical analysis. Moreover, we identify that the concentration of attention probabilities increases the probability matrix norm, leading to a gradient exploding.

Downloads

Next from EMNLP 2025

HD-PiSSA: High-Rank Distributed Orthogonal Adaptation

Similar lecture

What Makes Chain-of-Thought Prompting Effective? A Counterfactual Study