English
Related papers

Related papers: Analyzing Latent Concepts in Code Language Models

200 papers

Faithful generation in large language models (LLMs) is challenged by knowledge conflicts between parametric memory and external context. Existing contrastive decoding methods tuned specifically to handle conflict often lack adaptability and…

Computation and Language · Computer Science 2025-08-28 Anant Khandelwal , Manish Gupta , Puneet Agrawal

Next token prediction has been the standard training objective used in large language model pretraining. Representations are learned as a result of optimizing for token-level perplexity. We propose Continuous Concept Mixing (CoCoMix), a…

Machine Learning · Computer Science 2025-02-13 Jihoon Tack , Jack Lanchantin , Jane Yu , Andrew Cohen , Ilia Kulikov , Janice Lan , Shibo Hao , Yuandong Tian , Jason Weston , Xian Li

Large Language Models (LLMs) for unsupervised code correctness evaluation have recently gained attention because they can judge if code runs as intended without requiring reference implementations or unit tests, which may be unavailable,…

Artificial Intelligence · Computer Science 2026-04-02 Bhrij Patel , Souradip Chakraborty , Mengdi Wang , Dinesh Manocha , Amrit Singh Bedi

Developing human understandable interpretation of large language models (LLMs) becomes increasingly critical for their deployment in essential domains. Mechanistic interpretability seeks to mitigate the issues through extracts…

Machine Learning · Computer Science 2026-01-30 Yuhang Liu , Erdun Gao , Dong Gong , Anton van den Hengel , Javen Qinfeng Shi

The integration of large language models (LLMs) into recommendation systems has revealed promising potential through their capacity to extract world knowledge for enhanced reasoning capabilities. However, current methodologies that adopt…

Information Retrieval · Computer Science 2025-10-17 Lingyu Mu , Hao Deng , Haibo Xing , Kaican Lin , Zhitong Zhu , Yu Zhang , Xiaoyi Zeng , Zhengxiao Liu , Zheng Lin , Jinxin Hu

As Large Language Models for Code (LM4Code) become integral to software engineering, establishing trust in their output becomes critical. However, standard accuracy metrics obscure the underlying reasoning of generative models, offering…

Software Engineering · Computer Science 2026-04-14 Dipin Khati , Daniel Rodriguez-Cardenas , David N. Palacio , Alejandro Velasco , Michele Tufano , Denys Poshyvanyk

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…

Computation and Language · Computer Science 2023-05-04 Ruochen Zhao , Shafiq Joty , Yongjie Wang , Tan Wang

Pretrained Large Language Models (LLMs) are prone to generating fluent yet factually incorrect text-a phenomenon known as hallucinations, undermining their reliability and utility in downstream tasks. We hypothesize that a generated text…

Computation and Language · Computer Science 2026-03-10 Koduvayur Subbalakshmi , Sabbir Hossain Ujjal , Venkata Krishna Teja Mangichetty , Nastaran Jamalipour Soofi

The opaque nature of Large Language Models (LLMs) has led to significant research efforts aimed at enhancing their interpretability, primarily through post-hoc methods. More recent in-hoc approaches, such as Concept Bottleneck Models…

Machine Learning · Computer Science 2025-02-20 Or Raphael Bidusa , Shaul Markovitch

Large Language Models (LLMs) excel at reasoning and planning when trained on chainof-thought (CoT) data, where the step-by-step thought process is explicitly outlined by text tokens. However, this results in lengthy inputs where many words…

Computation and Language · Computer Science 2025-09-03 DiJia Su , Hanlin Zhu , Yingchen Xu , Jiantao Jiao , Yuandong Tian , Qinqing Zheng

Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular,…

Computation and Language · Computer Science 2023-11-06 Chen Shani , Jilles Vreeken , Dafna Shahaf

Interpreting the internal reasoning of vision-language models is essential for deploying AI in safety-critical domains. Concept-based explainability provides a human-aligned lens by representing a model's behavior through semantically…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Ehud Gordon , Meir Yossef Levi , Guy Gilboa

We propose a novel framework ConceptX, to analyze how latent concepts are encoded in representations learned within pre-trained language models. It uses clustering to discover the encoded concepts and explains them by aligning with a large…

Computation and Language · Computer Science 2022-06-28 Hassan Sajjad , Nadir Durrani , Fahim Dalvi , Firoj Alam , Abdul Rafae Khan , Jia Xu

The transparency of deep learning models is essential for clinical diagnostics. Concept Bottleneck Model provides clear decision-making processes for diagnosis by transforming the latent space of black-box models into human-understandable…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Yiheng Dong , Yi Lin , Xin Yang

Deep Learning models encode rich semantic information in their hidden representations. However, it remains challenging to understand which parts of this information models actually rely on when making predictions. A promising line of…

Machine Learning · Computer Science 2026-02-04 Xuemin Yu , Ankur Garg , Samira Ebrahimi Kahou , Hassan Sajjad

The opacity of deep neural networks remains a challenge in deploying solutions where explanation is as important as precision. We present ConceptX, a human-in-the-loop framework for interpreting and annotating latent representational space…

Computation and Language · Computer Science 2022-11-15 Firoj Alam , Fahim Dalvi , Nadir Durrani , Hassan Sajjad , Abdul Rafae Khan , Jia Xu

Multilingual Large Language Models (LLMs) develop cross-lingual abilities despite being trained on limited parallel data. However, they often struggle to generate responses in the intended language, favoring high-resource languages such as…

Computation and Language · Computer Science 2025-06-02 Elnaz Rahmati , Alireza S. Ziabari , Morteza Dehghani

The organization of latent knowledge within large-scale models poses unique challenges when addressing overlapping representations and optimizing contextual accuracy. Conceptual redundancies embedded across layers often result in…

Computation and Language · Computer Science 2025-03-26 Joseph Sakau , Evander Kozlowski , Roderick Thistledown , Basil Steinberger

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Computation and Language · Computer Science 2026-02-12 Weihao Liu , Dehai Min , Lu Cheng

Large language models handle single-turn generation well, but multi-turn interactions still require the model to reconstruct user intent and task state from an expanding token history because internal representations do not persist across…

Computation and Language · Computer Science 2025-12-11 Vishwas Hegde , Vindhya Shigehalli
‹ Prev 1 2 3 10 Next ›