Singapore

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.

EMNLP 2023

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

mechanistic interpretability

llms

math

interpretability

reasoning

## 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*

EMNLP 2025

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

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.

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

Efficient inference has become crucial for hyper-scale AI models, including large language models, as their parameter count continues to increase for enhanced performance.
This necessity holds true regardless of the computing environment, whether it be mobile devices or cloud servers.
Quantization emerges as a solution to alleviate the computational burden during inference.
By representing models with a reduced bit-width, quantization minimizes the frequency of DRAM access while fully exploiting the parallelism of operations through a dense matrix format.
Consequently, quantized models achieve low end-to-end latency and optimize resource utilization by addressing both memory and computing bottlenecks.
In this paper, we propose a straightforward post-training quantization scheme, called \textsc{Z-Fold}, that fully utilizes the feature of the Transformer structure widely employed in large language models.

A Frustratingly Easy Post-Training Quantization Scheme for LLMs

Pre-trained large language models (LLMs) reflect the inherent social biases of their training corpus. Many methods have been proposed to mitigate this issue, but they often fail to debias or they sacrifice model accuracy. We use *conceptors*--a soft projection method--to identify and remove the bias subspace in LLMs such as BERT and GPT. We propose two methods of applying conceptors (1) bias subspace projection by post-processing by the conceptor NOT operation; and (2) a new architecture, conceptor-intervened BERT (CI-BERT), which explicitly incorporates the conceptor projection into all layers during training. We find that conceptor post-processing achieves state-of-the-art (SoTA) debiasing results while maintaining LLMs' performance on the GLUE benchmark. Further, it is robust in various scenarios and can mitigate intersectional bias efficiently by its AND operation on the existing bias subspaces. Although CI-BERT's training takes all layers' bias into account and can beat its post-processing counterpart in bias mitigation, CI-BERT reduces the language model accuracy. We also show the importance of carefully constructing the bias subspace. The best results are obtained by removing outliers from the list of biased words, combining them (via the OR operation), and computing their embeddings using the sentences from a cleaner corpus.

Conceptor-Aided Debiasing of Large Language Models

We ask the question: Are there widespread disparities in machine translations of names across race/ethnicity, and gender? We hypothesize that the translation quality of names and surrounding context will be lower for names associated with US racial and ethnic minorities due to these systems’ tendencies to standardize language to predominant language patterns. We develop a dataset of names that are strongly demographically aligned and propose a translation evaluation procedure based on round-trip translation. We analyze the effect of name demographics on translation quality using generalized linear mixed effects models and find that the ability of translation systems to correctly translate female-associated names is significantly lower than male-associated names. This effect is particularly pronounced for female-associated names that are also associated with racial (Black) and ethnic (Hispanic) minorities. This disparity in translation quality between social groups for something as personal as someone's name has significant implications for people's professional, personal, and cultural identities, self-worth and ease of communication. Our findings suggest that more MT research is needed to improve the translation of names and to provide high-quality service for users regardless of gender, race, and ethnicity.

A Rose by Any Other Name would not Smell as Sweet: Social Bias in Names Mistranslation | VIDEO

Post-training quantization (PTQ) of transformer language models faces significant challenges due to the existence of detrimental outliers in activations. We observe that these outliers are concentrated in specific channels and are asymmetric across channels. To address this issue, we propose the Outlier Suppression+ (OS+) framework, which contains the channel-wise shifting for asymmetry and channel-wise scaling for concentration. We show that these operations can be seamlessly migrated into subsequent modules while maintaining equivalence. Second, we propose a fast and stable scheme to calculate effective shifting and scaling values. The channel-wise shifting aligns the center of each channel for removal of outlier asymmetry. The channel-wise scaling quantitatively evaluates changes brought by migration and quantization for better quantization burden balance. We validate our OS+ under both standard and fine-grained quantization settings with models including BERT, OPT, BLOOM, BLOOMZ, and LLaMA. Comprehensive results across various tasks demonstrate the superiority of our approach. Especially, with standard quantization, OS+ can achieve near-floating-point performance on both small models and large language models on 8-bit and 6-bit. Besides, we establish a new state-of-the-art for 4-bit BERT with 15.5\% improvement. Our code is available at \url{https://github.com/ModelTC/Outlier_Suppression_Plus}.

Outlier Suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling

Studies in bias and fairness in natural language processing have primarily examined social biases within a single language and/or across few attributes (e.g. gender, race). However, biases can manifest differently across various languages for individual attributes. As a result, it is critical to examine biases within each language and attribute. Of equal importance is to study how these biases compare across languages and how the biases are affected when training a model on multilingual data versus monolingual data. We present a bias analysis across Italian, Chinese, English, Hebrew, and Spanish on the downstream sentiment analysis task to observe whether specific demographics are viewed more positively. We study bias similarities and differences across these languages and investigate the impact of multilingual vs. monolingual training data. We adapt existing sentiment bias templates in English to Italian, Chinese, Hebrew, and Spanish for four attributes: race, religion, nationality, and gender. Our results reveal similarities in bias expression such as favoritism of groups that are dominant in each language's culture (e.g. majority religions and nationalities). Additionally, we find an increased variation in predictions across protected groups, indicating bias amplification, after multilingual finetuning in comparison to multilingual pretraining.

Comparing Biases and the Impact of Multilingual Training across Multiple Languages

Performant vision-language (VL) models like CLIP represent captions using a single vector. How much information about language is lost in this bottleneck? We first curate CompPrompts, a set of increasingly compositional image captions that VL models should be able to capture (e.g., single object, to object+property, to multiple interacting objects). Then, we train text-only recovery probes that aim to reconstruct captions from single-vector text representations produced by several VL models. This approach does not require images, allowing us to test on a broader range of scenes compared to prior work. We find that: 1) CLIP’s text encoder falls short on more compositional inputs, including object relationships, attribute-object association, counting, and negations; 2) some text encoders work significantly better than others; and 3) text-only recovery performance predicts multimodal matching performance on ControlledImCaps: a new evaluation benchmark we collect and release consisting of fine-grained compositional images and captions. Specifically, our results suggest text-only recoverability is a necessary (but not sufficient) condition for modeling compositional factors in contrastive VL models. We release our datasets and code.

Text encoders bottleneck compositionality in contrastive vision-language models | VIDEO

LIME has emerged as one of the most commonly referenced tools in explainable AI (XAI) frameworks that is integrated into critical machine learning applications (e.g., healthcare and finance). However, its stability remains little explored, especially in the context of text data, due to the unique text-space constraints. To address these challenges, in this paper, we first evaluate the inherent instability of LIME on text data to establish a baseline, and then propose a novel algorithm XAIFooler to perturb text inputs and manipulate explanations that casts investigation on the stability of LIME as a text perturbation optimization problem. XAIFooler conforms to the constraints to preserve text semantics and original prediction with small perturbations, and introduces Rank-biased Overlap (RBO) as a key part to guide the optimization of XAIFooler that satisfies all the requirements for explanation similarity measure. Extensive experiments on real-world text datasets demonstrate that XAIFooler significantly outperforms all baselines by large margins in its ability to manipulate LIME's explanations with high semantic preservability.

“Are Your Explanations Reliable?” Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack

In this work, we consider the problem of intersectional group fairness in the classification setting, where the objective is to learn discrimination-free models in the presence of several intersecting sensitive groups.
First, we illustrate various shortcomings of existing fairness measures commonly used to capture intersectional fairness. 
Then, we propose a new definition called the $\alpha$-Intersectional Fairness, which combines the absolute and the relative performance across sensitive groups and can be seen as a generalization of the notion of differential fairness. 
We highlight several desirable properties of the proposed definition and analyze its relation to other fairness measures.
Finally, we benchmark multiple popular in-processing fair machine learning approaches using our new fairness definition and show that they do not achieve any improvement over a simple baseline. 
Our results reveal that the increase in fairness measured by previous definitions hides a ``leveling down'' effect, i.e., degrading the best performance over groups rather than improving the worst one.

Fair Without Leveling Down: A New Intersectional Fairness Definition

Propaganda is a form of deceptive narratives that instigate or mislead the public, usually with a political purpose. In this paper, we aim to identify propaganda in political news at two fine-grained levels: sentence-level and token-level. We observe that propaganda content is more likely to be embedded in sentences that attribute causality or assert contrast to nearby sentences, as well as seen in opinionated evaluation, speculation and discussions of future expectation. Hence, we propose to incorporate both local and global discourse structures for propaganda discovery and construct two teacher models for identifying PDTB-style discourse relations between nearby sentences and common discourse roles of sentences in a news article respectively. We further devise two methods to incorporate the two types of discourse structures for propaganda identification by either using teacher predicted probabilities as additional features or soliciting guidance in a knowledge distillation framework. Experiments on the benchmark dataset demonstrate that leveraging guidance from discourse structures can significantly improve both precision and recall of propaganda content identification.

Discourse Structures Guided Fine-grained Propaganda Identification

Science journalism refers to the task of reporting technical findings of a scientific paper as a less technical news article to the general public audience. We aim to design an automated system to support this real-world task (i.e., automatic science journalism ) by 1) introducing a newly-constructed and real-world dataset (SciTechNews), with tuples of a publicly-available scientific paper, its corresponding news article, and an expert-written short summary snippet; 2) proposing a novel technical framework that integrates a paper's discourse structure with its metadata to guide generation; and, 3) demonstrating with extensive automatic and human experiments that our model outperforms other baseline methods (e.g. Alpaca and ChatGPT) in elaborating a content plan meaningful for the target audience, simplify the information selected, and produce a coherent final report in a layman's style.

Downloads

Next from EMNLP 2023

A Frustratingly Easy Post-Training Quantization Scheme for LLMs

Similar lecture

The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It