Related papers: Language Models Can Predict Their Own Behavior
Large language models (LMs) are currently trained to predict tokens given document prefixes, enabling them to directly perform long-form generation and prompting-style tasks which can be reduced to document completion. Existing pretraining…
We investigate whether internal activations in language models can be used to detect arithmetic errors. Starting with a controlled setting of 3-digit addition, we show that simple probes can accurately decode both the model's predicted…
An important aspect in developing language models that interact with humans is aligning their behavior to be useful and unharmful for their human users. This is usually achieved by tuning the model in a way that enhances desired behaviors…
Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question, but it is unclear if the stated reasoning is a faithful explanation of the model's actual reasoning…
We investigate whether the success of a zero-shot Chain-of-Thought (CoT) process can be predicted before completion. We discover that a probing classifier, based on LLM representations, performs well \emph{even before a single token is…
Chain-of-Thought (CoT) monitoring has emerged as a compelling method for detecting harmful behaviors such as reward hacking for reasoning models, under the assumption that models' reasoning processes are informative of such behaviors. In…
Pre-trained language models (PLMs) may fail in giving reliable estimates of their predictive uncertainty. We take a close look into this problem, aiming to answer two questions: (1) Do PLMs learn to become calibrated in the training…
Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT…
Pre-trained language models (LMs) have shown remarkable reasoning performance using explanations or chain-of-thoughts (CoT)) for in-context learning. On the other hand, these reasoning tasks are usually presumed to be more approachable for…
Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this ability also heightens the risk of identity impersonation. To the best of our knowledge, no…
Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…
Language models are susceptible to bias, sycophancy, backdoors, and other tendencies that lead to unfaithful responses to the input context. Interpreting internal states of language models could help monitor and correct unfaithful behavior.…
Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contrast raises a central question- Can LMs likewise learn to…
We propose a novel approach to conformal prediction for generative language models (LMs). Standard conformal prediction produces prediction sets -- in place of single predictions -- that have rigorous, statistical performance guarantees. LM…
Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the safety of prompts before invoking target models. However,…
Large Language Models (LLMs) have started to demonstrate the ability to persuade humans, yet our understanding of how this dynamic transpires is limited. Recent work has used linear probes, lightweight tools for analyzing model…
Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…
Large language models (LLMs) rely on safety alignment to avoid responding to malicious user inputs. Unfortunately, jailbreak can circumvent safety guardrails, resulting in LLMs generating harmful content and raising concerns about LLM…
Current research found the issue of Early Answering in large language models (LLMs), where the models already have an answer before generating the Chain-of-Thought (CoT). This phenomenon suggests a potential lack of necessary dependency…
Language models (LMs) are pre-trained on raw text datasets to generate text sequences token-by-token. While this approach facilitates the learning of world knowledge and reasoning, it does not explicitly optimize for linguistic competence.…