United States

We introduce the Principled Reasoning and Acting (PRAct) framework, a novel LLM agent for learning and enforcing action principles from trajectory data.

EMNLP 2024

PRACT: Optimizing Principled Reasoning and Acting of LLM Agent

llm agent

prompt optimization

principles

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

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 ACL 2025". 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 need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

We study attribute control in language models through the method of Causal Average Treatment Effect (Causal ATE). Existing methods for the attribute control task in Language Models (LMs) check for the co-occurrence of words in a sentence with the attribute of interest, and control for them. However, spurious correlation of the words with the attribute in the training dataset, can cause models to hallucinate the presence of the attribute when presented with the spurious correlate during inference. We show that the simple perturbation-based method of Causal ATE removes this unintended effect. Specifically, we ground it in the problem of toxicity mitigation, where a significant challenge lies in the inadvertent bias that often emerges towards protected groups post detoxification. We show that this unintended bias can be solved by the use of the Causal ATE metric. We provide experimental validations for our claims and release our code (anonymously) here: \href{https://github.com/causalate-mitigates-bias/causal-ate-mitigates-bias}{github.com/causalate-mitigates-bias/causal-ate-mitigates-bias}.

Causal ATE Mitigates Unintended Bias in Controlled Text Generation

Text Segmentation (TS) is the task of segmenting bodies of text into coherent blocks, mostly defined by the topics each segment contains. Historically, techniques in this area have been unsupervised, with more success recently coming from supervised methods instead. Although these approaches see better performance, they require training data and upfront training time. We propose a new method called Coherence, where we use sentence embeddings to pull representational keywords as the main constructor of sentences when comparing them to one another. Additionally, we include a storage of previously found keywords for the purposes of creating a more accurate segment representation instead of just the immediate sentence in question. We show improved results over current state-of-the-art unsupervised techniques when analyzed using Pk and WindowDiff scores. Coherence also requires no fine-tuning.

Words That Stick: Using Keyword Cohesion to Improve Text Segmentation

English relative clauses are a critical test case for theories of syntactic processing. Expectation- and memory-based accounts make opposing predictions, and behavioral experiments have found mixed results. We present a technical extension of Lossy Context Surprisal (LCS) and use it to model relative clause processing in three behavioral experiments. LCS predicts key results at distinct retention rates, showing that task-dependent memory demands can account for discrepant behavioral patterns in the literature.

Lossy Context Surprisal Predicts Task-Dependent Patterns in Relative Clause Processing

Language Models (LMs) excel in natural language processing tasks for English but show reduced performance in most other languages. This problem is commonly tackled by continually pre-training and fine-tuning these models for said languages. A significant issue in this process is the limited vocabulary coverage in the original model’s tokenizer, leading to inadequate representation of new languages and necessitating an expansion of the tokenizer. The initialization of the embeddings corresponding to new vocabulary items presents a further challenge. Current strategies require cross-lingual embeddings and lack a solid theoretical foundation as well as comparisons with strong baselines. In this paper, we first establish theoretically that initializing within the convex hull of existing embeddings is a good initialization, followed by a novel but simple approach, Constrained Word2Vec (CW2V), which does not require cross-lingual embeddings. Our study evaluates different initialization methods for expanding RoBERTa and LLaMA 2 across four languages and five tasks. The results show that CW2V performs equally well or even better than more advanced techniques. Additionally, simpler approaches like multivariate initialization perform on par with these advanced methods indicating that efficient large-scale multilingual continued pretraining can be achieved even with simpler initialization methods.

An Empirical Comparison of Vocabulary Expansion and Initialization Approaches For Language Models

Hierarchical text classification (HTC) is the task of assigning labels to a text within a structured space organized as a hierarchy. Recent works treat HTC as a conventional multilabel classification problem, therefore evaluating it as such. We instead propose to evaluate models based on specifically designed hierarchical metrics and we demonstrate the intricacy of metric choice and prediction inference method. We introduce a new challenging dataset and we evaluate fairly, recent sophisticated models, comparing them with a range of simple but strong baselines, including a new theoretically motivated loss. Finally, we show that those baselines are very often competitive with the latest models. This highlights the importance of carefully considering the evaluation methodology when proposing new methods for HTC.

Revisiting Hierarchical Text Classification: Inference and Metrics

Structural priming is a widely used psycholinguistic paradigm to study human sentence representations. In this work we introduce SPAWN, a cognitively motivated parser that can generate quantitative priming predictions from contemporary theories in syntax which assume a lexicalized grammar. By generating and testing priming predictions from competing theoretical accounts, we can infer which assumptions from syntactic theory are useful for characterizing the representations humans build when processing sentences. As a case study, we use SPAWN to generate priming predictions from two theories (Whiz-Deletion and Participial-Phase) which make different assumptions about the structure of English relative clauses. By modulating the reanalysis mechanism that the parser uses and strength of the parser's prior knowledge, we generated nine sets of predictions from each of the two theories. Then, we tested these predictions using a novel web-based comprehension-to-production priming paradigm. We found that while the some of the predictions from the Participial-Phase theory aligned with human behavior, none of the predictions from the the Whiz-Deletion theory did, thus suggesting that the Participial-Phase theory might better characterize human relative clause representations.

SPAWNing Structural Priming Predictions from a Cognitively Motivated Parser

This paper evaluates whether large language models (LLMs) exhibit cognitive fan effects, similar to those discovered by Anderson in humans, after being pre-trained on human textual data. We conduct two sets of in-context recall experiments designed to elicit fan effects. Consistent with human results, we find that LLM recall uncertainty, measured via token probability, is influenced by the fan effect. Our results show that removing uncertainty disrupts the observed effect. The experiments suggest the fan effect is consistent whether the fan value is induced in-context or in the pre-training data. Finally, these findings provide in-silico evidence that fan effects and typicality are expressions of the same phenomena.

Large Language Model Recall Uncertainty is Modulated by the Fan Effect

State of the art models in automatic speech recognition have shown remarkable im- provements due to modern self-supervised (SSL) transformer-based architectures such as wav2vec 2.0 (Baevski et al., 2020). However, how these models encode phonetic informa- tion is still not well understood. We explore whether SSL speech models display a linguis- tic property that characterizes human speech perception: language specificity. We show that while wav2vec 2.0 displays an overall lan- guage specificity effect when tested on Hindi vs. English, it does not resemble human speech perception when tested on finer-grained differ- ences in Hindi speech contrasts.

Self-supervised speech representations display some human-like cross-linguistic perceptual abilities

Grapheme-to-Phoneme (G2P) correspondences form foundational frameworks of tasks such as text-to-speech (TTS) synthesis or automatic speech recognition. The G2P process involves taking words in their written form and generating their pronunciation. In this paper, we critique the status quo definition of a grapheme, currently a forced alignment process relating a single character to either a phoneme or a blank unit, that underlies the majority of modern approaches. We develop a linguisticallymotivated redefinition from simple concepts such as vowel and consonant count and word length and offer a proof-of-concept implementation based on a multi-binary neural classification task. Our model achieves competitive results with a 31.86% Word Error Rate on a standard benchmark, while generating linguistically meaningful grapheme segmentations.

One-Vs-Rest Neural Network English Grapheme Segmentation: A Linguistic Perspective

Counterspeech presents a viable alternative to banning or suspending users for hate speech while upholding freedom of expression. How- ever, writing effective counterspeech is chal- lenging for moderators/users. Hence, develop- ing suggestion tools for writing counterspeech is the need of the hour. One critical challenge in developing such a tool is the lack of qual- ity and diversity of the responses in the ex- isting datasets. Hence, we introduce a new dataset - CROWDCOUNTER containing 3,425 hate speech-counterspeech pairs spanning six different counterspeech types (empathy, humor, questioning, warning, shaming, contradiction), which is the first of its kind. The design of our annotation platform itself encourages an- notators to write type-specific, non-redundant and high-quality counterspeech. We evaluate two frameworks for generating counterspeech responses - vanilla and type-controlled prompts - across four large language models. In terms of metrics, we evaluate the responses using rel- evance, diversity and quality. We observe that Flan-T5 is the best model in the vanilla frame- work across different models. Type-specific prompts enhance the relevance of the responses, although they might reduce the language qual- ity. DialoGPT proves to be the best at following the instructions and generating the type-specific counterspeech accurately.

Downloads

Next from EMNLP 2024

Causal ATE Mitigates Unintended Bias in Controlled Text Generation

Similar lecture

Unveiling Privacy Risks in LLM Agent Memory

.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 2024

Causal ATE Mitigates Unintended Bias in Controlled Text Generation

Similar lecture

Unveiling Privacy Risks in LLM Agent Memory

Downloads