12 accepted papers
Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over substantive qualities. This bias manifests as overreliance on features like length, structure, and style, leading to issues…
Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior may be explicit, i.e. verbalized in the model's chain-of-thought (CoT), or implicit, where the CoT appears benign thus…
As LLMs become more agentic, a critical risk emerges: attackers can \emph{decompose} harmful goals into stateful, benign subtasks that trick LLM agents into executing them without realizing the harmful intent in the same context. The challenge lies in the existing shallow safety alignment techniques…
Search is an ability foundational in many important tasks, and recent studies have shown that large language models (LLMs) struggle to perform search robustly. It is unknown whether this inability is due to a lack of data, insufficient model parameters, or fundamental limitations of the transformer…
Recent work shows that causal facts can be effectively extracted from LLMs through prompting, facilitating the creation of causal graphs for causal inference tasks. However, it is unclear if this success is limited to explicitly-mentioned causal facts in the pretraining data which the model can memo…
Large language models (LLMs) are trained on vast amounts of text from the internet, which contains both factual and misleading information about the world. While unintuitive from a classic view of LMs, recent work has shown that the truth value of a statement can be elicited from the model’s represe…
In-context learning (ICL) is an important paradigm for adapting large language models (LLMs) to new tasks, but the generalization behavior of ICL remains poorly understood. We investigate the inductive biases of ICL from the perspective of feature bias: which feature ICL is more likely to use given…
Given the intractably large size of the space of proofs, any model that is capable of general deductive reasoning must generalize to proofs of greater complexity. Recent studies have shown that large language models (LLMs) possess some abstract deductive reasoning ability given chain-of-thought prom…
While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work has explored using counterfactually-augmented data (CAD)—data generated by mini…
The term ‘spurious correlations’ has been used in NLP to informally denote any undesirable feature-label correlations. However, a correlation can be undesirable because (i) the feature is irrelevant to the label (e.g. punctuation in a review), or (ii) the feature’s effect on the label depends on the…
To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our qu…
Accented speech poses significant challenges for state-of-the-art automatic speech recognition (ASR) systems. Accent is a property of speech that lasts throughout an utterance in varying degrees of strength. This makes it hard to isolate the influence of accent on individual speech sounds. We propos…