English
Related papers

Related papers: Jacobian Scopes: token-level causal attributions i…

200 papers

Generative Language Models rely on autoregressive decoding to produce the output sequence token by token. Many tasks such as preference optimization, require the model to produce task-level output consisting of multiple tokens directly by…

Computation and Language · Computer Science 2025-01-30 Mingyu Derek Ma , Yanna Ding , Zijie Huang , Jianxi Gao , Yizhou Sun , Wei Wang

Existing studies have introduced method-based reasoning and scope extension as approaches to enhance Large Language Model (LLM) performance beyond direct matrix mappings. Building on these foundations, this paper summarizes and integrates…

Artificial Intelligence · Computer Science 2025-10-14 Hong Su

Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representations that abstractly describe graph traversal algorithms and step-by-step reasoning in…

Artificial Intelligence · Computer Science 2026-05-28 Phuong Minh Nguyen , Tien Huu Dang , Naoya Inoue

Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured conceptual representations within these models, it remains unclear whether they functionally rely on…

Computation and Language · Computer Science 2026-04-21 Ningyu Xu , Qi Zhang , Xipeng Qiu , Xuanjing Huang

Large Language Models (LLMs) exhibit impressive capabilities yet suffer from sensitivity to slight input context variations, hampering reliability. Conventional metrics like accuracy and perplexity fail to assess local prediction…

Computation and Language · Computer Science 2026-02-12 Deyuan Liu , Zecheng Wang , Zhanyue Qin , Zhiying Tu , Dianhui Chu , Dianbo Sui

Probabilistic next-token prediction trained using cross-entropy loss is the basis of most large language models. Given a sequence of previous values, next-token prediction assigns a probability to each possible next value in the vocabulary.…

Machine Learning · Statistics 2025-05-19 Jacob Trauger , Ambuj Tewari

Large Language Models (LLMs) have shown promise in clinical applications through prompt engineering, allowing flexible clinical predictions. However, they struggle to produce reliable prediction probabilities, which are crucial for…

Artificial Intelligence · Computer Science 2024-12-05 Bowen Gu , Rishi J. Desai , Kueiyu Joshua Lin , Jie Yang

Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate exceptional performance, they face robustness challenges due to…

Computation and Language · Computer Science 2024-06-18 Yuhang Zhou , Paiheng Xu , Xiaoyu Liu , Bang An , Wei Ai , Furong Huang

Recent works have argued that high-level semantic concepts are encoded "linearly" in the representation space of large language models. In this work, we study the origins of such linear representations. To that end, we introduce a simple…

Computation and Language · Computer Science 2024-03-07 Yibo Jiang , Goutham Rajendran , Pradeep Ravikumar , Bryon Aragam , Victor Veitch

Deep learning models achieve high predictive performance but lack intrinsic interpretability, hindering our understanding of the learned prediction behavior. Existing local explainability methods focus on associations, neglecting the causal…

Machine Learning · Computer Science 2025-09-18 Niklas Penzel , Joachim Denzler

In large language models (LLMs), each block operates on the residual stream to map input token sequences to output token distributions. However, most of the interpretability literature focuses on internal latent representations, leaving…

Machine Learning · Computer Science 2026-02-03 Riccardo Ali , Francesco Caso , Christopher Irwin , Pietro Liò

Language models trained on large text corpora encode rich distributional information about real-world environments and action sequences. This information plays a crucial role in current approaches to language processing tasks like question…

Machine Learning · Computer Science 2023-02-07 Belinda Z. Li , William Chen , Pratyusha Sharma , Jacob Andreas

This paper systematically compares different methods of deriving item-level predictions of language models for multiple-choice tasks. It compares scoring methods for answer options based on free generation of responses, various…

Computation and Language · Computer Science 2024-03-05 Polina Tsvilodub , Hening Wang , Sharon Grosch , Michael Franke

Recent work utilizes Large Language Models (LLMs) for topic modeling, generating comprehensible topic labels for given documents. However, their performance has mainly been evaluated qualitatively, and there remains room for quantitative…

Computation and Language · Computer Science 2024-06-26 Tomoki Doi , Masaru Isonuma , Hitomi Yanaka

Language models have consistently grown to compress more world knowledge into their parameters, but the knowledge that can be pretrained into them is upper-bounded by their parameter size. Especially the capacity of Small Language Models…

Computation and Language · Computer Science 2026-05-18 Szilvia Ujváry , Louis Béthune , Pierre Ablin , João Monteiro , Marco Cuturi , Michael Kirchhof

Recently, prompt tuning \cite{lester2021power} has gradually become a new paradigm for NLP, which only depends on the representation of the words by freezing the parameters of pre-trained language models (PLMs) to obtain remarkable…

Computation and Language · Computer Science 2022-01-31 Pan He , Yuxi Chen , Yan Wang , Yanru Zhang

Large-scale pre-trained vision foundation models, such as CLIP, have become de facto backbones for various vision tasks. However, due to their black-box nature, understanding the underlying rules behind these models' predictions and…

Computer Vision and Pattern Recognition · Computer Science 2023-10-17 Haozhe Chen , Junfeng Yang , Carl Vondrick , Chengzhi Mao

The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-token error probabilities, posits an inherent limitation for long autoregressive outputs. Our…

Computation and Language · Computer Science 2026-05-07 Mikhail L. Arbuzov , Sisong Bei , Ziwei Dong , Dmitri Kalaev , Alexey A. Shvets

Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but whether they encode semantic operations producing those…

Computation and Language · Computer Science 2026-05-26 Nura Aljaafari , Marco Valentino , André Freitas

Vision Large Language Models (VLLMs) usually take input as a concatenation of image token embeddings and text token embeddings and conduct causal modeling. However, their internal behaviors remain underexplored, raising the question of…

Computation and Language · Computer Science 2025-05-16 Houjing Wei , Yuting Shi , Naoya Inoue