Singapore

Recent work suggests that large language models (LLMs) achieve higher accuracy on multi-step reasoning tasks when prompted to generate intermediate reasoning steps, or a chain of thought (CoT), before their final answer. However, it is unclear how exactly CoTs improve LLMs&#39; accuracy, and in particular, if LLMs use their CoTs to reason to their final answers. This paper tries to answer this question with respect to arithmetic word problems, by (i) evaluating the correctness of LLMs&#39; CoTs, and (ii) using causal abstraction to assess if the intermediate tokens produced as part of a CoT causally impact LLMs&#39; final answers, in line with the reasoning described by the CoT. We find that for CoT-prompted LLMs, correct answers to arithmetic problems are highly correlated with correct CoTs, and that when LLMs produce correct CoTs, they realize to a fairly large extent the causal models suggested by their CoTs. Higher degrees of realization also seem associated with better overall accuracy on the arithmetic problems. These findings suggest that some CoT-prompted LLMs may do better on multi-step arithmetic reasoning at least partly because}they use their CoTs to reason to their final answers. However, for some LLMs, other internal processes may also be involved.

EMNLP 2023

Causal Abstraction for Chain-of-Thought Reasoning in Arithmetic Word Problems

causal abstraction

arithmetic reasoning

chain-of-thought

multi-step reasoning

faithfulness

explainability

interpretability

#### *Message from the General Chair, Aline Villavicencio*
I’m delighted and honoured to welcome you to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), taking place in the beautiful city of Rabat, in Morocco, in March 24-29, 2026. EACL is the flagship European conference of the Association and EACL 2026 proudly continues our field’s tradition of excellence in scholarship, innovation, and inclusivity. I am deeply grateful to the many volunteers whose dedication, generosity, and tireless efforts have made this conference possible.
For the first time EACL is being hosted in the African continent. This is an important milestone for our community, and we are grateful to our Moroccan hosts for enabling this historic moment by bringing this edition of EACL to Rabat. We are also delighted that the Second Arabic NLP School is co-located with EACL. We hope attendees enjoy this wonderful opportunity to strengthen ties with the Computational Linguistics communities across the African continent. *[Read full message](https://drive.google.com/file/d/14NlmHvwM6fPJuMmOvVh7K0vtQbEyv3SZ/view?usp=sharing)* 

<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://underline.io/events/522/reception','_blank')">Go to Workshops and Tutorials Program</button></html>

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to EACL 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.eacl.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/eacl2026

Registration Required

EACL 2026

Welcome to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL). EACL 2026 will be held in Rabat, Morocco, from March 24–29, 2026. 

Recent work suggests that large language models (LLMs) achieve higher accuracy on multi-step reasoning tasks when prompted to generate intermediate reasoning steps, or a chain of thought (CoT), before their final answer. However, it is unclear how exactly CoTs improve LLMs' accuracy, and in particular, if LLMs use their CoTs to reason to their final answers. This paper tries to answer this question with respect to arithmetic word problems, by (i) evaluating the correctness of LLMs' CoTs, and (ii) using causal abstraction to assess if the intermediate tokens produced as part of a CoT causally impact LLMs' final answers, in line with the reasoning described by the CoT. We find that for CoT-prompted LLMs, correct answers to arithmetic problems are highly correlated with correct CoTs, and that when LLMs produce correct CoTs, they realize to a fairly large extent the causal models suggested by their CoTs. Higher degrees of realization also seem associated with better overall accuracy on the arithmetic problems. These findings suggest that some CoT-prompted LLMs may do better on multi-step arithmetic reasoning at least partly because}they use their CoTs to reason to their final answers. However, for some LLMs, other internal processes may also be involved.

workshop paper

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

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Large Language Models (LLMs) struggle to perform such reasoning consistently. Here we propose an approach to pinpoint and rectify multi-hop reasoning failures through targeted memory injections on LLM attention heads. First, we analyze the per-layer activations of GPT-2 models in response to single and multi-hop prompts. We then propose a mechanism that allows users to inject pertinent prompt-specific information, which we refer to as "memories," at critical LLM locations during inference. By thus enabling the LLM to incorporate additional relevant information during inference, we enhance the quality of multi-hop prompt completions. We show empirically that a simple, efficient, and targeted memory injection into a key attention layer can often increase the probability of the desired next token in multi-hop tasks, by up to 424%.

Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models

Transformer-based Large Language Models (LLMs) are the state-of-the-art for natural language tasks. Recent work has attempted to decode, by reverse engineering the role of linear layers, the internal mechanisms by which LLMs arrive at their final predictions for text completion tasks. Yet little is known about the specific role of attention heads in producing the final token prediction. We propose Attention Lens, a tool that enables researchers to translate the outputs of attention heads into vocabulary tokens via learned attention-head-specific transformations called lenses. Preliminary findings from our trained lenses indicate that attention heads play highly specialized roles in language models.

Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism

Despite recent advances in the field of explainability, much remains unknown about the algorithms that neural networks learn to represent. Recent work has attempted to understand trained models by decomposing them into functional circuits (Csordás et al., 2020; Lepori et al., 2023). To advance this research, we developed NeuroSurgeon, a python library that can be used to discover and manipulate subnetworks within models in the Huggingface Transformers library (Wolf et al., 2019). NeuroSurgeon is freely available at https:
//github.com/mlepori1/NeuroSurgeon.

NeuroSurgeon: A Toolkit for Subnetwork Analysis

Explanations for AI are expected to help human users understand AI-driven predictions. Evaluating plausibility, the helpfulness of the explanations, is therefore essential for developing eXplainable AI (XAI) that can really aid human users. Here we propose a human-centric evaluation platform1 to measure plausibility of explanations in the context of eXplainable Knowledge Graph Completion (XKGC). The target audience of the platform are researchers and practitioners who want to 1) investigate real needs and interests of their target users in XKGC, 2) evaluate the plausibility of XKGC methods.

Human-Understandable Knowledge Graph Completion

Establishing whether language models can use contextual information in a human-plausible way is important to ensure their safe adoption in real-world settings. However, the questions of when and which parts of the context affect model generations are typically tackled separately, and current plausibility evaluations are practically limited to a handful of artificial benchmarks. To address this, we introduce Plausibility Evaluation of Context Reliance (PECoRe), an end-to-end interpretability framework designed to quantify context usage in language models' generations. Our approach leverages model internals to (i) contrastively identify context-sensitive target tokens in generated texts and (ii) link them to contextual cues justifying their prediction. We use PECoRe to quantify the plausibility of context-aware machine translation models, comparing model rationales with human annotations across several discourse-level phenomena. Finally, we apply our method to unannotated generations to identify context-mediated predictions and highlight instances of (im)plausible context usage in model translations.

Quantifying the Plausibility of Context Reliance in Neural Machine Translation

Enhancing Interpretability using Human Similarity Judgements to Prune Word Embeddings

The increasing interest in probing the linguistic capabilities of large language models (LLMs) has long reached the area of semantics and pragmatics, including the phenomenon of presuppositions. In this study, we investigate a phenomenon that, however, has not yet been investigated, i.e., the phenomenon of anti-presupposition and the principle that accounts for it, the Maximize Presupposition! principle (MP!). Through an experimental investigation using psycholinguistic data and four open-source BERT model variants, we explore how language models handle different antipresuppositions and whether they apply the MP! principle in their predictions. Further, we examine whether fine-tuning with Natural Language Inference data impacts adherence to the MP! principle. Our findings reveal that LLMs tend to replicate context-based n-grams rather than follow the MP! principle, with fine-tuning not enhancing their adherence. Notably, our results further indicate a striking difficulty of LLMs to correctly predict determiners, in relatively simple linguistic contexts.

When your Language Model cannot even do Determiners right: Probing for Anti-Presuppositions and the Maximize Presupposition! Principle

How do sequence models represent their decision-making process? Prior work suggests that Othello-playing neural network learned nonlinear models of the board state (Li et al., 2023a). In this work, we provide evidence of a closely related linear representation of the board. In particular, we show that probing for “my colour” vs. “opponent’s colour” may be a simple yet powerful way to interpret the model’s internal state. This precise understanding of the internal representations allows us to control the model’s behaviour with simple vector arithmetic. Linear representations enable significant interpretability progress, which we
demonstrate with further exploration of how the world model is computed.

Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Explanations are meaningful only if it is understandable for human users. In daily life, humans explain to each other in natural language. However, eXplainable AI (XAI) identifies, e. g., important attributes from tabular data as explanations to a prediction, which are often difficult for humans to understand, especially when they
have no AI background. To solve the limitation, we aim to generate text-based comprehensive explanations conditioned on the important features selected by an XAI method. We expect the explanations can borrow strength from XAI and Large Language Models (LLMs), integrating the concrete information extracted by XAI from tabular data and the general domain knowledge retained in LLM from large corpus.

Natural Language Explanation for Tabular Data

We train a transformer network on the task of performing additions of two integers, achieving near perfect test-set accuracy with just 8000 positive training examples. We compute both learning curves (accuracy as a function of training set size) and model selection curves (accuracy as a function of embedding dimension and of number of layers). We observe that the number of dimension plays the biggest role, whereas the number of layers does not make a big difference after four layers. While the network generalises well from training to testing set, we did not observe any transfer-learning benefits when learning subtraction, having to relearn it from scratch. Current work involves probing the attention heads to understand the different roles played by positional embedding and the digit embedding (our conjecture is that query and key should be attending to position, while value should be attending to the actual digit). This distinction would not be possible when analysing words.

Downloads

Next from EMNLP 2023

Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models

Similar lecture

LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-hop Arithmetics

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EMNLP 2023

Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models

Similar lecture

LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-hop Arithmetics

Downloads