The paper investigates how large language models (LLMs) represent and retrieve singular and plural entities for coreference resolution. Using mechanistic interpretability and attention pattern analysis, the authors identify specific attention heads that encode coreference information, detect plural entities, and guide pronoun prediction. The study also shows that LLMs prefer plural pronouns for ontologically similar entities linked by "and", mirroring human preferences.
arXiv:2606. 16407v1 Announce Type: cross Abstract: Faithful and robust pronoun use is important for fair and coherent generations, yet large language models largely fail when multiple referents use different pronouns.
The study uses sparse autoencoders (SAEs) to probe how the Pythia-70M language model encodes grammatical number. By identifying and manipulating SAE‑derived features such as "plural noun" and "generate a plural verb," the authors show that removing these features forces the model to produce singular verbs, and vice versa. Similar asymmetries were observed in larger models (Gemma‑2‑2b and Llama‑3.1‑8b), indicating a privative representation of number in English.
MechaTerp-TRACE is a new framework that systematically ablates individual components of language models to measure their causal contribution to producing a named entity. By applying TRACE to thirteen instruction‑tuned dense decoder models, the study finds that a small set of positionally fixed components consistently carry the most influence across models and prompts, while the remaining support is evenly distributed. This suggests that entity knowledge is largely embedded in generic generation machinery rather than in isolated, findable components.
The study examines how vision‑language models handle multi‑turn pragmatic interpretation in iterated reference games, where participants repeatedly identify novel referents using language. Researchers compared human performance with that of several models, manipulating context by varying its amount, order, and relevance. While humans consistently performed well, the models could use prior context but struggled to build relevant context for effective interpretation, indicating missing core skills for efficient linguistic collaboration.
arXiv:2608. 13484v1 Announce Type: cross Abstract: When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims.
arXiv:2609.14207v1 Announce Type: new Abstract: We propose to finetune vision-language models to generate more pragmatically optimal referring expressions by transforming observations of incremental...
This study evaluates whether large language models (LLMs) can reliably replace or complement human research assistants in linguistically complex annotation. In a controlled annotation task, 73 human a...
As previous research on annotator disagreement in discourse phenomena has shown, understanding text coherence varies considerably from one individual to another. To explore this phenomenon, we created two corpora with multiple annotations of Czech texts, accompanied by annotators' explanations of their choices.
arXiv:2603. 23485v2 Announce Type: replace-cross Abstract: Standard evaluation practices assume that large language model (LLM) outputs are stable when prompts are embedded in contextually equivalent discourses.
When large language models (LLMs) fail to generalize or make haphazard errors in reasoning, it is often taken as evidence that LLMs are not truly reasoning, but rather performing a kind of pattern matching. The implication is that people's behavior does not exhibit the same types of failures because human reasoning uses principled and abstract world models.
arXiv:2512. 06276v3 Announce Type: replace-cross Abstract: Referring Expression Comprehension (REC) is a vision-language task that localizes a specific image region based on a textual description.
arXiv:2606. 13607v1 Announce Type: new Abstract: When large language models (LLMs) fail to generalize or make haphazard errors in reasoning, it is often taken as evidence that LLMs are not truly reasoning, but rather performing a kind of pattern matching.