Understanding a discourse requires tracking entities and the relations that hold between them. While Large Language Models (LLMs) perform well on relational reasoning, the mechanism by which they bind entities, relations, and attributes remains unclear. We study discourse-level relational binding and show that LLMs encode it via a Cell-based Binding Representation (CBR): a low-dimensional linear subspace in which each “cell” corresponds to an entity–relation index pair, and bound attributes are retrieved from the corresponding cell during inference. Using controlled multi-sentence data annotated with entity and relation indices, we identify the CBR subspace by decoding these indices from attribute-token activations with Partial Least Squares regression. Across domains and two model families, the indices are linearly decodable and form a grid-like geometry in the projected space. We further find that context-specific CBR representations are related by translation vectors in activation space, enabling cross-context transfer. Finally, activation patching shows that manipulating this subspace systematically changes relational predictions and that perturbing it disrupts performance, providing causal evidence that LLMs rely on CBR for relational binding.

Munachiso S Nwadike, Zangir Iklassov, Toluwani Aremu, Tatsuya Hiraoka, Benjamin Heinzerling, Velibor Bojkovic, Hilal AlQuabeh, Martin Takáč, Kentaro Inui. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Entity tracking is essential for complex reasoning.To perform in-context entity tracking, language models (LMs) must bind an entity to its attribute (e.g., bind a container to its content) to recall attribute for a given entity.For example, given a context mentioning "The coffee is in Box Z, the stone is in Box M, the map is in Box H", to infer "Box Z contains the coffee" later, LMs must bind "Box Z" to "coffee".To explain the binding behaviour of LMs, Feng and Steinhardt (2023) introduce a Binding ID mechanism and state that LMs use a abstract concept called Binding ID (BI) to internally mark entity-attribute pairs.However, they have not captured the Ordering ID (OI) from entity activations that directly determines the binding behaviour.In this work, we provide a novel view of the BI mechanism by localizing OI and proving the causality between OI and binding behaviour.Specifically, by leveraging dimension reduction methods (e.g., PCA), we discover that there exists a low-rank subspace in the activations of LMs, that primarily encodes the order (i.e., OI) of entity and attribute.Moreover, we also discover the causal effect of OI on binding that when editing representations along the OI encoding direction, LMs tend to bind a given entity to other attributes accordingly.For example, by patching activations along the OI encoding direction we can make the LM to infer "Box Z contains the stone" and "Box Z contains the map".The code and datasets used in this paper are available at https://github.com/cl-tohoku/OI-Subspace.

Static word embeddings (SWE) and contextualized word embeddings (CWE) are the foundation of modern natural language processing. However, these embeddings suffer from spatial bias in the form of anisotropy, which has been demonstrated to reduce their performance. A method to alleviate the anisotropy is the “whitening” transformation. Whitening is a standard method in signal processing and other areas, however, its effect on SWE and CWE is not well understood. In this study, we conduct an experiment to elucidate the effect of whitening on SWE and CWE. The results indicate that whitening predominantly removes the word frequency bias in SWE, and biases other than the word frequency bias in CWE.

Bi-encoder architectures for distantlysupervised relation extraction are designed to make use of the complementary information found in text and knowledge graphs (KG).However, current architectures suffer from two drawbacks.They either do not allow any sharing between the text encoder and the KG encoder at all, or, in case of models with KG-to-text attention, only share information in one direction.Here, we introduce cross-stitch bi-encoders, which allow full interaction between the text encoder and the KG encoder via a cross-stitch mechanism.The cross-stitch mechanism allows sharing and updating representations between the two encoders at any layer, with the amount of sharing being dynamically controlled via cross-attention-based gates.Experimental results on two relation extraction benchmarks from two different domains show that enabling full interaction between the two encoders yields strong improvements.

We present Semi-Structured Explanations for COPA (COPA-SSE), a new crowdsourced dataset of 9,747 semi-structured, English common sense explanations for Choice of Plausible Alternatives (COPA) questions. The explanations are formatted as a set of triple-like common sense statements with ConceptNet relations but freely written concepts. This semi-structured format strikes a balance between the high quality but low coverage of structured data and the lower quality but high coverage of free-form crowdsourcing. Each explanation also includes a set of human-given quality ratings. With their familiar format, the explanations are geared towards commonsense reasoners operating on knowledge graphs and serve as a starting point for ongoing work on improving such systems. The dataset is available at https://github.com/a-brassard/copa-sse.

Pretrained language models have been suggested as a possible alternative or complement to structured knowledge bases.However, this emerging LM-as-KB paradigm has so far only been considered in a very limited setting, which only allows handling 21k entities whose name is found in common LM vocabularies.Furthermore, a major benefit of this paradigm, i.e., querying the KB using natural language paraphrases, is underexplored.Here we formulate two basic requirements for treating LMs as KBs: (i) the ability to store a large number facts involving a large number of entities and (ii) the ability to query stored facts.We explore three entity representations that allow LMs to handle millions of entities and present a detailed case study on paraphrased querying of facts stored in LMs, thereby providing a proof-of-concept that language models can indeed serve as knowledge bases.

Pride Kavumba, Benjamin Heinzerling, Ana Brassard, Kentaro Inui. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Pretrained contextual and non-contextual subword embeddings have become available in over 250 languages, allowing massively multilingual NLP.However, while there is no dearth of pretrained embeddings, the distinct lack of systematic evaluations makes it difficult for practitioners to choose between them.In this work, we conduct an extensive evaluation comparing non-contextual subword embeddings, namely FastText and BPEmb, and a contextual representation method, namely BERT, on multilingual named entity recognition and part-of-speech tagging.We find that overall, a combination of BERT, BPEmb, and character representations works well across languages and tasks.A more detailed analysis reveals different strengths and weaknesses: Multilingual BERT performs well in medium-to high-resource languages, but is outperformed by non-contextual subword embeddings in a low-resource setting.* Work done while at HITS. 1 While language-agnostic, these approaches are not language-independent.See Appendix B for a discussion.

Recent work has validated the importance of subword information for word representation learning. Since subwords increase parameter sharing ability in neural models, their value should be even more pronounced in low-data regimes. In this work, we therefore provide a comprehensive analysis focused on the usefulness of subwords for word representation learning in truly low-resource scenarios and for three representative morphological tasks: fine-grained entity typing, morphological tagging, and named entity recognition. We conduct a systematic study that spans several dimensions of comparison: 1) type of data scarcity which can stem from the lack of task-specific training data, or even from the lack of unannotated data required to train word embeddings, or both; 2) language type by working with a sample of 16 typologically diverse languages including some truly low-resource ones (e.g. Rusyn, Buryat, and Zulu); 3) the choice of the subword-informed word representation method. Our main results show that subword-informed models are universally useful across all language types, with large gains over subword-agnostic embeddings. They also suggest that the effective use of subwords largely depends on the language (type) and the task at hand, as well as on the amount of available data for training the embeddings and task-based models, where having sufficient in-task data is a more critical requirement.

We introduce automatic verification as a post-processing step for entity linking (EL).The proposed method trusts EL system results collectively, by assuming entity mentions are mostly linked correctly, in order to create a semantic profile of the given text using geospatial and temporal information, as well as fine-grained entity types.This profile is then used to automatically verify each linked mention individually, i.e., to predict whether it has been linked correctly or not.Verification allows leveraging a rich set of global and pairwise features that would be prohibitively expensive for EL systems employing global inference.Evaluation shows consistent improvements across datasets and systems.In particular, when applied to state-of-theart systems, our method yields an absolute improvement in linking performance of up to 1.7 F 1 on AIDA/CoNLL'03 and up to 2.4 F 1 on the English TAC KBP 2015 TEDL dataset.* The majority of this work was done during an internship at Microsoft Research Asia. 1 We use entity to refer to both real-word entities and to their corresponding entries in the KB.

Selectional preferences have long been claimed to be essential for coreference resolution.However, they are mainly modeled only implicitly by current coreference resolvers.We propose a dependencybased embedding model of selectional preferences which allows fine-grained compatibility judgments with high coverage.We show that the incorporation of our model improves coreference resolution performance on the CoNLL dataset, matching the state-of-the-art results of a more complex system.However, it comes with a cost that makes it debatable how worthwhile such improvements are.