Detecting responses that retrieval-augmented generation does not ground in its context trades speed against accuracy: surface checks miss paraphrased fabrication, sampling-based methods cost extra generations. Hidden-state probes sit between the two, but every existing one reads the generating model's own activations,...
Michael Rathmayr, Adam Kovacs, Gábor Recski· 0 citations
Large language models (LLMs) increasingly mediate human communication, from drafting emails to summarizing scientific reports, yet whether they faithfully preserve a speaker's position remains largely untested. We model AI-mediated communication as a two-step generation-extraction pipeline: one LLM produces an argument...
Ling-Chong Liu, Yan-Fei Zhou, Jacob Bien et al.· 0 citations
Answer correctness is encoded as a recoverable geometric direction in the hidden states of language models. We show that the mean displacement from incorrect to correct answer representations, computed at approximately 70\% of model depth from fifty labeled examples with no parameter updates, yields a scoring direction...
Marcus Armstrong, Navid Ayoobi, Pradham Mummaleti et al.· 0 citations
Nowadays, emojis are often replacing words. Yet computational systems still oversimplify them. Most existing approaches treat emojis as static sentiment indicators and overlook their emotional distributions. In this study, we propose an emoji-aware emotion analysis framework based on a Twitter (X) dataset of 100,000 em...
Public vs. private universities is a debatable issue, and it creates polarization on social media in Bangladesh. Debate on quality, jobs, and prestige is passionate among the students, parents, and graduates, the majority of whom speak Bengali, a low-resource language. To measure this polarization, this paper introduce...
Safaruzzaman Shovo, Monowar Islam, Asif Hossain et al.· 0 citations
Data quality now matters as much as compute for training language models. Much training data comes from human annotation of text, and interpretive annotation has no ground truth that could settle what is "accurate". Two lines of work respond to this. One combines annotators into a "ground truth" and measures how well t...
Identical utterance choices can arise from different communicative causes, and identical interpretations can leave different traces in what a listener learns. Rational Speech Act (RSA) models treat interpretation as inference over speaker meaning, but standard one-shot RSA does not intrinsically distinguish these causa...
Yonghyeon Gwon, Elliot Murphy, Chun Kee Chung· 0 citations
This paper investigates the task of predicting job experience levels in recruitment texts, aiming to automatically identify the qualifications required for positions. Unlike traditional text classification, recruitment texts typically possess explicit internal structures, with different paragraphs playing disproportion...
Celia Liang, Eddie Wu, Shiqi Wang et al.· 0 citations
Large language models (LLMs) receive each user message as plain text, even when it combines text from different sources. For example, a user may paste text into a prompt and keep typing a comment directly below it. We study absorption: a phenomenon where the model treats a trailing user comment as part of the pasted te...
Mechanistic interpretability usually studies fully trained models, yet the computations that drive a behaviour can change while the model is still learning the task. On the Indirect Object Identification task, a model should continue with the name mentioned once rather than the name mentioned twice. Pythia models pass...
Long-context LLMs can now ingest entire online discussion threads, but understanding their social discourse requires more than reading a long document: models must track parent-reply relations, turning points, scoped subtrees, cross-branch contrasts, and participant trajectories. To test this structure-aware social rea...
Xin-Yi Liu, R. Khaziev, Dilek Hakkani-Tur et al.· 0 citations
Despite rapid progress in automating scientific research, generating promising and well grounded research solutions remains a central challenge. We isolate research ideation as a standalone task and build our solution on the intuition that a challenge in one field can often be addressed by a mechanism that solved an an...
Jia-Rui Liu, Ren-Jie Tao, Yi-Wei Liao et al.· 0 citations
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
MIT News · Artificial Intelligence· news.mit.eduAug 31, 2026
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
