Singapore

Due to language models&#39; propensity to generate toxic or hateful responses, several techniques were developed to align model generations with users&#39; preferences. Despite the effectiveness of such methods in improving the safety of model interactions, their impact on models&#39; internal processes is still poorly understood. 
In this work, we apply popular detoxification approaches to several language models and quantify their impact on the resulting models&#39; prompt dependence using feature attribution methods. We evaluate the effectiveness of counter-narrative fine-tuning and compare it with reinforcement learning-driven detoxification, observing differences in prompt reliance between the two methods despite their similar detoxification performances.

EMNLP 2023

Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence

interpretability

detoxification

language models

Due to language models' propensity to generate toxic or hateful responses, several techniques were developed to align model generations with users' preferences. Despite the effectiveness of such methods in improving the safety of model interactions, their impact on models' internal processes is still poorly understood. 
In this work, we apply popular detoxification approaches to several language models and quantify their impact on the resulting models' prompt dependence using feature attribution methods. We evaluate the effectiveness of counter-narrative fine-tuning and compare it with reinforcement learning-driven detoxification, observing differences in prompt reliance between the two methods despite their similar detoxification performances.

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.

In this talk, we address the limitations of existing natural language recommendation explanation systems by proposing a novel approach using knowledge graphs (KGs). Unlike previous methods relying on subjective item reviews, our KG-based approach generates fact-grounded, personalized explanations that consider user preferences and item features objectively. By leveraging collaborative filtering and user-item representations, our model consistently outperforms state-of-the-art models in natural language explainable recommendation, enhancing user understanding and trust in the system.

Knowledge-grounded Natural Language Recommendation Explanation

Usual model-agnostic explanation methods create artificial instances by slightly perturbing real instances, capturing shifts in model decisions. However, such methods rely on initial data and only provide explanations of the decision for these. To tackle these problems, we propose Therapy, the first global and model-agnostic explanation method adapted to text which requires no input dataset. Therapy generates texts following the distribution learned by a classifier through cooperative generation. Because it does not rely on initial samples, it allows to generate explanations even when data is absent (e.g., for confidentiality reasons). Moreover, conversely to existing methods that combine multiple local explanations into a global one, Therapy offers a global overview of the model behavior on the input space. Our experiments show that although using no input data to generate samples, Therapy provides insightful information about features used by the classifier that is competitive with the ones from methods relying on input samples and outperforms them when input samples are not specific to the studied model.

"Honey, Tell Me What's Wrong'', Global Explanation of Textual Discriminative Models through Cooperative Generation

Large language models (LLMs) that do not give consistent answers across contexts are problematic when used for tasks with expectations of consistency–e.g. question-answering, explanations, etc. Our work presents an evaluation benchmark for self-consistency in cases of under-specification where two or more answers can be correct. We conduct a series of behavioral experiments on the OpenAI model suite using an ambiguous integer sequence completion task. We find that average consistency ranges from 67% to 82%, far higher than would be predicted if a model’s consistency was random, and increases as model capability improves. Furthermore, we show that models tend to maintain self-consistency across a series of robustness checks, including prompting speaker changes and sequence length changes. These results suggest that self-consistency arises as an emergent capability without specifically training for it. Despite this, we find that models are uncalibrated when judging their own consistency, with models displaying both over- and under-confidence. We also propose a nonparametric test for determining from token output distribution whether a model assigns non-trivial probability to alternative answers. Using this test, we find that despite increases in self-consistency, models usually place significant weight on alternative, inconsistent answers. This distribution of probability mass provides evidence that even highly self-consistent models internally compute multiple possible responses.

Self-Consistency of Large Language Models under Ambiguity

We present a study that aims to localize where exactly in a PLM word contextualization happens by investigating representations of polysemous words in the basic BERT uncased 12 layer architecture. We ﬁnd word meaning transformation to occur strongly in Self-Attention and Activations sub-layer as compared to the Output sub-layers of BERT.

Where exactly does contextualization in a PLM happen?

The Backpack is a Transformer alternative shown to improve interpretability in English language modeling by decomposing predictions into a weighted sum of token sense components. However, Backpacks' reliance on token-defined meaning raises questions as to their potential for languages other than English, a language for which subword tokenization provides a reasonable approximation for lexical items. In this work, we train, evaluate, interpret, and control Backpack language models in character-tokenized Chinese, in which words are often composed of many characters. We find that our (134M parameter) Chinese Backpack language model performs comparably to a (104M parameter) Transformer, and learns rich character-level meanings that log-additively compose to form word meanings. In SimLex-style lexical semantic evaluations, simple averages of Backpack character senses outperform input embeddings from a Transformer. We find that complex multi-character meanings are often formed by using the same per-character sense weights consistently across context. Exploring interpretability-through control, we show that we can localize a source of gender bias in our Backpacks to specific character senses and intervene to reduce the bias.

Character-level Chinese Backpack Language Models

Unveiling Multilinguality in Transformer Models: Exploring Language Specificity in Feed-Forward Networks

Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings

Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One vastly successful class of neural models is transformers. When used as an encoder, a transformer produces contextual representation of words in the input sentence. In this work, we propose a new model of contextual word representation, not from a neural perspective, but from a purely syntactic and probabilistic perspective. Specifically, we design a conditional random field that models discrete latent representations of all words in a sentence as well as dependency arcs between them; and we use mean field variational inference for approximate inference. Strikingly, we find that the computation graph of our model resembles transformers, with correspondences between dependencies and self-attention and between distributions over latent representations and contextual embeddings of words. Experiments show that our model performs competitively to transformers on small to medium sized datasets. We hope that our work could help bridge the gap between traditional syntactic and probabilistic approaches and cutting-edge neural approaches to NLP, and inspire more linguistically-principled neural approaches in the future.

Probabilistic Transformer: A Probabilistic Dependency Model for Contextual Word Representation

Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing

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.

Next from EMNLP 2023

Knowledge-grounded Natural Language Recommendation Explanation