Mathematical reasoning in large language models (LMs) has garnered significant attention in recent work, but there is a limited understanding of how these models process and store information related to arithmetic tasks within their architecture.
In order to improve our understanding of this aspect of language models, we present a mechanistic interpretation of Transformer-based LMs on arithmetic questions using a causal mediation analysis framework.
By intervening on the activations of specific model components and measuring the resulting changes in predicted probabilities, we identify the subset of parameters responsible for specific predictions.
This provides insights into how information related to arithmetic is processed by LMs.
Our experimental results indicate that LMs process the input by transmitting the information relevant to the query from mid-sequence early layers to the final token using the attention mechanism. Then, this information is processed by a set of MLP modules, which generate result-related information that is incorporated into the residual stream.
To assess the specificity of the observed activation dynamics, we compare the effects of different model components on arithmetic queries with other tasks, including number retrieval from prompts and factual knowledge questions.

A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis | VIDEO

Recent work has shown that language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities. However, it is unclear whether LMs perform these tasks by cheating with answers memorized from pretraining corpus, or, via a multi-step reasoning mechanism. In this paper, we try to answer this question by exploring a mechanistic interpretation of LMs for multi-step reasoning tasks. Concretely, we hypothesize that the LM implicitly embeds a reasoning tree resembling the correct reasoning process within it. We test this hypothesis by introducing a new probing approach (called MechanisticProbe) that recovers the reasoning tree from the model’s attention patterns. We use our probe to analyze two LMs: GPT-2 on a synthetic task (k-th smallest element), and LLaMA on two simple language-based reasoning tasks (ProofWriter \& AI2 Reasoning Challenge). We show that MechanisticProbe is able to detect the information of the reasoning tree from the model’s attentions for most examples, suggesting that the LM indeed is going through a process of multi-step reasoning within its architecture in many cases.

Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models

While automatic dialogue tutors hold great potential in making education personalized and more accessible, research on such systems has been hampered by a lack of sufficiently large and high-quality datasets. Collecting such datasets remains challenging, as recording tutoring sessions raises privacy concerns and crowdsourcing leads to insufficient data quality. To address this, we propose a framework to generate such dialogues by pairing human teachers with a Large Language Model (LLM) prompted to represent common student errors.
We describe how we use this framework to collect MathDial, a dataset of 3k one-to-one teacher-student tutoring dialogues grounded in multi-step math reasoning problems. While models like GPT-3 are good problem solvers, they fail at tutoring because they generate factually incorrect feedback or are prone to revealing solutions to students too early. To overcome this, we let teachers provide learning opportunities to students by guiding them using various scaffolding questions according to a taxonomy of teacher moves. We demonstrate MathDial and its extensive annotations can be used to finetune models to be more effective tutors (and not just solvers). We confirm this by automatic and human evaluation, notably in an interactive setting that measures the trade-off between student solving success and telling solutions. The dataset is released publicly.

MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems

*Data Synthesis* is a promising way to train a small model with very little labeled data. One approach for data synthesis is to leverage the rich knowledge from large language models to synthesize pseudo training examples for small models, making it possible to achieve both data and compute efficiency at the same time. However, a key challenge in data synthesis is that the synthesized dataset often suffers from a large distributional discrepancy from the *real task* data distribution. Thus, in this paper, we propose *Synthesis Step by Step* (**S3**), a data synthesis framework that shrinks this distribution gap by iteratively extrapolating the errors made by a small model trained on the synthesized dataset on a small real-world validation dataset using a large language model. Extensive experiments on multiple NLP tasks show that our approach improves the performance of a small model by reducing the gap between the synthetic dataset and the real data, resulting in significant improvement compared to several baselines: 9.48% improvement compared to ZeroGen and 2.73% compared to GoldGen, and at most 15.17% improvement compared to the small model trained on human-annotated data.

Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models

In human-AI collaboration, users typically form a mental model of the AI system, which captures the user's beliefs about when the system performs well and when it does not.
The construction of this mental model is guided by both the system's veracity as well as the system output presented to the user e.g., the system's confidence and an explanation for the prediction.
However, modern NLP systems are seldom calibrated and are often confidently incorrect about their predictions, which violates users’ mental model and erodes their trust.
In this work, we design a study where users bet on the correctness of an NLP system, and use it to study the evolution of user trust as a response to these trust-eroding events and how the user trust is rebuilt as a function of time after these events.
We find that even a few highly inaccurate confidence estimation instances are enough to damage users' trust in the system and performance, which does not easily recover over time.
We further find that users are more forgiving to the NLP system if it is unconfidently correct rather than confidently incorrect, even though, from a game-theoretic perspective, their payoff is equivalent.
Finally, we find that each user can entertain multiple mental models of the system based on the type of the question.
These results highlight the importance of confidence calibration in developing user-centered NLP applications to avoid damaging user trust and compromising the collaboration performance.

A Diachronic Perspective on User Trust in AI under Uncertainty

Topic models help us make sense of large text collections. Automatically evaluating their output and determining the optimal number of topics are both longstanding challenges, with no effective automated solutions to date. This paper proposes using large language models (LLMs) for these tasks. We find that LLMs appropriately assess the resulting topics, correlating more strongly with human judgments than existing automated metrics. However, the setup of the evaluation task is crucial — LLMs perform better on coherence ratings of word sets than on intrustion detection. We find that LLMs can also assist us in guiding us towards a reasonable number of topics. In actual applications, topic models are typically used to answer a research question related to a collection of texts. We can incorporate this research question in the prompt to the LLM, which helps estimating the optimal number of topics.

Revisiting Automated Topic Model Evaluation with Large Language Models | VIDEO

Textbooks are one of the main mediums for delivering high-quality education to students.
In particular, explanatory and illustrative visuals play a key role in retention, comprehension and general transfer of knowledge.
However, many textbooks lack these interesting visuals to support student learning.
In this paper, we investigate the effectiveness of vision-language models to automatically enhance textbooks with images from the web.
We collect a dataset of e-textbooks in the math, science, social science and business domains.
We then set up a text-image matching task that involves retrieving and appropriately assigning web images to textbooks, which we frame as a matching optimization problem.
Through a crowd-sourced evaluation, we verify that (1) while the original textbook images are rated higher, automatically assigned ones are not far behind, and (2) the precise formulation of the optimization problem matters.
We release the dataset of textbooks with an associated image bank to inspire further research in this intersectional area of computer vision and NLP for education.

Enhancing Textbooks with Visuals from the Web for Improved Learning

**Are you attending this poster session virtually?** 
In-person printed posters are available for in-person attendees only.
 
**Are you attending this poster session in person?** 
Hybrid posters are displayed in the East Foyer.

PS5 (In-person) Posters, Demo, Industry, Findings

poster

**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.

MRINMAYA SACHAN

7

11

Presentations

A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis | VIDEO

Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models

MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems

Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models

A Diachronic Perspective on User Trust in AI under Uncertainty

Revisiting Automated Topic Model Evaluation with Large Language Models | VIDEO

Enhancing Textbooks with Visuals from the Web for Improved Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES