English
Related papers

Related papers: Inference-Time Intervention: Eliciting Truthful An…

200 papers

Techniques that enhance inference through increased computation at test-time have recently gained attention. In this survey, we investigate the current state of LLM Inference-Time Self-Improvement from three different perspectives:…

Computation and Language · Computer Science 2024-12-20 Xiangjue Dong , Maria Teleki , James Caverlee

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in…

Computation and Language · Computer Science 2024-01-23 Pengyu Wang , Dong Zhang , Linyang Li , Chenkun Tan , Xinghao Wang , Ke Ren , Botian Jiang , Xipeng Qiu

Numerous decision-making tasks require estimating causal effects under interventions on different parts of a system. As practitioners consider using large language models (LLMs) to automate decisions, studying their causal reasoning…

Machine Learning · Computer Science 2024-12-24 Tejas Kasetty , Divyat Mahajan , Gintare Karolina Dziugaite , Alexandre Drouin , Dhanya Sridhar

Large language models (LLMs) have demonstrated remarkable performance across various real-world tasks. However, they often struggle to fully comprehend and effectively utilize their input contexts, resulting in responses that are unfaithful…

Computation and Language · Computer Science 2024-09-18 Qingru Zhang , Xiaodong Yu , Chandan Singh , Xiaodong Liu , Liyuan Liu , Jianfeng Gao , Tuo Zhao , Dan Roth , Hao Cheng

Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical…

Ensuring factuality is essential for the safe use of Large Language Models (LLMs) in high-stakes domains such as medicine and law. Conformal inference provides distribution-free guarantees, but existing approaches are either overly…

Machine Learning · Computer Science 2026-02-03 Kangjun Noh , Seongchan Lee , Ilmun Kim , Kyungwoo Song

Large Language Models (LLMs) have revolutionized inference across diverse natural language tasks, with larger models performing better but at higher computational costs. We propose a confidence-driven strategy that dynamically selects the…

Computation and Language · Computer Science 2026-02-26 Bo-Wei Chen , Chung-Chi Chen , An-Zi Yen

Natural language explanations play a fundamental role in Natural Language Inference (NLI) by revealing how premises logically entail hypotheses. Recent work has shown that the interaction of large language models (LLMs) with theorem provers…

Computation and Language · Computer Science 2025-06-02 Xin Quan , Marco Valentino , Louise A. Dennis , André Freitas

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text. We propose modeling factual queries as constraint satisfaction problems and use this framework to…

Computation and Language · Computer Science 2024-04-18 Mert Yuksekgonul , Varun Chandrasekaran , Erik Jones , Suriya Gunasekar , Ranjita Naik , Hamid Palangi , Ece Kamar , Besmira Nushi

Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora, making them powerful tools for various applications. To make LLMs more usable, aligning them with human preferences is essential.…

Computation and Language · Computer Science 2024-10-21 Mozhi Zhang , Pengyu Wang , Chenkun Tan , Mianqiu Huang , Dong Zhang , Yaqian Zhou , Xipeng Qiu

Large language models (LLMs) show potential as simulators of human behavior, offering a scalable way to study responses to interventions. However, because LLMs are trained largely on observational data, interventions in experiments with…

Computation and Language · Computer Science 2026-05-21 Victoria Lin , Taedong Yun , Maja Matarić , John Canny , Arthur Gretton , Alexander D'Amour

Although Large Language Models (LLMs) are showing impressive performance on a wide range of Natural Language Processing tasks, researchers have found that they still have limited ability to conduct induction. Recent works mainly adopt…

Computation and Language · Computer Science 2024-03-12 Wangtao Sun , Haotian Xu , Xuanqing Yu , Pei Chen , Shizhu He , Jun Zhao , Kang Liu

Large Language Models (LLMs) are able to provide assistance on a wide range of information-seeking tasks. However, model outputs may be misleading, whether unintentionally or in cases of intentional deception. We investigate the ability of…

Computation and Language · Computer Science 2024-07-17 Betty Li Hou , Kejian Shi , Jason Phang , James Aung , Steven Adler , Rosie Campbell

Activation engineering is becoming increasingly popular as a means of online control of large language models (LLMs). In this work, we extend the idea of inference-time steering with vectors that represent a behavioral direction of interest…

Machine Learning · Computer Science 2024-11-26 Christopher M. Ackerman

We demonstrate that LLMs may learn indicators of document usefulness and modulate their updates accordingly. We introduce random strings ("tags") as indicators of usefulness in a synthetic fine-tuning dataset. Fine-tuning on this dataset…

Machine Learning · Computer Science 2024-07-16 Dmitrii Krasheninnikov , Egor Krasheninnikov , Bruno Mlodozeniec , Tegan Maharaj , David Krueger

One paradigm of language model (LM) fine-tuning relies on creating large training datasets, under the assumption that high quantity and diversity will enable models to generalize to novel tasks after post-training. In practice, gathering…

Machine Learning · Computer Science 2025-10-10 Emre Can Acikgoz , Cheng Qian , Heng Ji , Dilek Hakkani-Tür , Gokhan Tur

Claim verification is an important problem in high-stakes settings, including health and finance. When information underpinning claims is incomplete or conflicting, uncertain answers may be more appropriate than binary true or false…

Artificial Intelligence · Computer Science 2026-05-20 Gabriel Freedman , Adam Dejl , Adam Gould , Mansi , Lihu Chen , Jianqi Jiang , Francesca Toni

Large Language Models (LLMs) are increasingly used for toxicity assessment in online moderation systems, where fairness across demographic groups is essential for equitable treatment. However, LLMs often produce inconsistent toxicity…

Computation and Language · Computer Science 2026-01-15 Jing Ren , Bowen Li , Ziqi Xu , Renqiang Luo , Shuo Yu , Xin Ye , Haytham Fayek , Xiaodong Li , Feng Xia

Current interactive systems with natural language interfaces lack the ability to understand a complex information-seeking request which expresses several implicit constraints at once, and there is no prior information about user preferences…