arXiv subjects

Aryaman Arora

Publications and source records attributed to Aryaman Arora.

At least 19 recordsLinked to original sources

arXiv2026

Verbalizing LLMs' assumptions to explain and control sycophancy

LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather than providing genuine assessment. We hypothesize that this behavior arises from LLMs' incorrect assumptions about the user, like underestimating how often users are seeking information over reassurance. We present Verbalized Assumptions, a framework for eliciting these assumptions from LLMs. Verbalized Assumptions provide insight into LLM sycophancy, delusion, and other safety issues: in social sycophancy datasets, "seeking validation" is the most frequent bigram in LLMs' assumptions. We provide evidence for a causal link between assumptions and sycophantic model behavior: we train linear probes on internal representations associated with Verbalized Assumptions and then use these probes for interpretable, fine-grained steering of social sycophancy. Finally, we identify a human-AI expectation gap that explains why LLMs default to sycophantic assumptions. On identical queries, people expect more objective and informative responses from AI than from other humans, but LLMs trained on human-human conversation do not account for this difference in expectations. Our work contributes a new understanding of assumptions as a mechanism for analyzing and controlling sycophancy.

cs.CL↗

arXiv2026

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment

The mechanisms behind LLMs' broad over-generalization beyond training examples remain unclear. Emergent misalignment (EM) offers a striking case study: finetuning on narrow tasks induces broad misalignment to semantically-unrelated test domains. In this work, we propose the Piggyback Hypothesis: the chat-template tokens can piggyback the finetuned behaviour onto out-of-domain queries. We validate this hypothesis by showing that subtle perturbations to the prefix (tokens preceding all user queries), or patching the prefix representations with those from the unfinetuned model, can restore alignment without changing the user query. Building on this finding, we propose Token-Regularized Finetuning (TReFT), which regularizes specific token representations during training to mitigate EM. Across different models and multiple EM-inducing datasets, TReFT reduces EM while preserving in-domain learning. On Llama-3.1-8B finetuned on the legal domain, TReFT achieves 33.5% more EM reduction than data interleaving with a retain set of aligned examples. We further show that TReFT extends to other narrow-finetuning settings, including abstention, tool use, and refusal (off-topic generalization is reduced by 54.3% on average), supporting the Piggyback Hypothesis. Broadly, our work highlights that LLMs may learn and generalize in unintended ways and suggests a path toward more constrained finetuning. It also calls for further study of how shared input features can piggyback model behavior across domains.

cs.CL↗

arXiv2026

Language Model Circuits Are Sparse in the Neuron Basis

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques which decompose the neuron basis into more interpretable units of model computation, such as sparse autoencoders (SAEs). However, not all neuron-based representations are uninterpretable. For the first time, we empirically show that MLP neurons are as sparse a feature basis as SAEs. We use this finding to develop an end-to-end gradient-based attribution pipeline for circuit tracing on the MLP neuron basis, which surfaces causally effective neurons on a variety of tasks. On a standard subject-verb agreement benchmark (Marks et al., 2025), a circuit of $\approx 10^2$ MLP neurons is enough to control model behaviour. On the multi-hop city-state-capital task from (Lindsey et al., 2025), we find a circuit in which small sets of neurons encode specific latent reasoning steps (e.g. mapping a city to its state), and can be steered to change the model's output. This work thus advances automated interpretability of language models without imposing additional training costs.

cs.CL↗

arXiv2026

PreFT: Prefill-only finetuning for efficient inference

Large language models can now be personalised efficiently at scale using parameter efficient finetuning methods (PEFTs), but serving user-specific PEFTs harms throughput, even with specialised kernels and memory management techniques. This is because, theoretically and empirically, a mismatch exists between prefill (processing a large number of tokens at once) and decode (generating a single token autoregressively): the latter has far lower throughput when serving multiple adapters. Rather than optimising performance relative to parameter count, for efficient multi-adapter serving, we instead ought to optimise performance relative to serving throughput. We therefore propose PreFT (Prefill-only Finetuning), wherein we only apply the adapter to prefill tokens and discard it afterwards. PreFT significantly increases throughput with minimal effect on performance. We develop and release an efficient implementation of two prefill-only PEFTs, LoRA and ReFT, on the vLLM inference engine. We first show that serving multi-user PreFTs is more efficient than traditional PEFTs ($1.9\times$ the throughput when serving $512$ adapters on Llama 3.1 70B). Then, we compare the performance of prefill-only vs. all-token adapters on a variety of supervised finetuning and reinforcement learning tasks with LMs at varying scales. On SFT, we observe that the evaluation loss of PreFTs is higher than PEFTs, but can be compensated by increasing rank with nearly no reduction in throughput. On RL, we consistently find that PreFTs approach parity with standard PEFTs. Together, this work validates prefill-only adaptation of LLMs as a more favourable accuracy-throughput tradeoff than existing PEFTs for personalised serving.

cs.LG↗

arXiv2026

ADAG: Automatically Describing Attribution Graphs

In language model interpretability research, \textbf{circuit tracing} aims to identify which internal features causally contributed to a particular output and how they affected each other, with the goal of explaining the computations underlying some behaviour. However, all prior circuit tracing work has relied on ad-hoc human interpretation of the role that each feature in the circuit plays, via manual inspection of data artifacts such as the dataset examples the component activates on. We introduce \textbf{ADAG}, an end-to-end pipeline for describing these attribution graphs which is fully automated. To achieve this, we introduce \textit{attribution profiles} which quantify the functional role of a feature via its input and output gradient effects. We then introduce a novel clustering algorithm for grouping features, and an LLM explainer--simulator setup which generates and scores natural-language explanations of the functional role of these feature groups. We run our system on known human-analysed circuit-tracing tasks and recover interpretable circuits, and further show ADAG can find steerable clusters which are responsible for a harmful advice jailbreak in Llama 3.1 8B Instruct.

cs.CL↗

arXiv2026

Mechanistic evaluation of Transformers and state space models

State space models (SSMs) for language modelling promise an efficient and performant alternative to quadratic-attention Transformers, yet show variable performance on recalling basic information from the context. While performance on synthetic tasks like Associative Recall (AR) can point to this deficiency, behavioural metrics provide little information as to \textit{why} -- on a mechanistic level -- certain architectures fail and others succeed. To address this, we conduct experiments on AR, and find that only Transformers and Based SSM models fully succeed at AR, with Mamba and DeltaNet close behind, while the other SSMs (H3, Hyena) fail. We then use causal interventions to explain why. We find that Transformers and Based learn to store key-value associations in-context using induction. By contrast, the SSMs seem to compute these associations only at the last state using a single layer. We further investigate the mechanism underlying the success of Mamba, and find novel evidence that Mamba \textit{does} implement induction: not via the SSM, but instead via short convolutions. Further experiments on a new hierarchical retrieval task, Associative Treecall (ATR), show that all architectures learn the same mechanism as they did for AR. Furthermore, we show that Mamba can learn Attention-like induction on ATR when short convolutions are removed. These results reveal that architectures with similar accuracy may still have substantive differences, motivating the adoption of mechanistic evaluations.

cs.CL↗

arXiv2025

CGELBank Annotation Manual v1.2

CGELBank is a treebank and associated tools based on a syntactic formalism for English derived from the Cambridge Grammar of the English Language (CGEL; Huddleston and Pullum, 2002). It is hosted on GitHub at https://github.com/nert-nlp/cgel. This document lays out the particularities of the CGELBank annotation scheme.

cs.CL↗

arXiv2025

Bayesian scaling laws for in-context learning

In-context learning (ICL) is a powerful technique for getting language models to perform complex tasks with no training updates. Prior work has established strong correlations between the number of in-context examples provided and the accuracy of the model's predictions. In this paper, we seek to explain this correlation by showing that ICL approximates a Bayesian learner. This perspective gives rise to a novel Bayesian scaling law for ICL. In experiments with \mbox{GPT-2} models of different sizes, our scaling law matches existing scaling laws in accuracy while also offering interpretable terms for task priors, learning efficiency, and per-example probabilities. To illustrate the analytic power that such interpretable scaling laws provide, we report on controlled synthetic dataset experiments designed to inform real-world studies of safety alignment. In our experimental protocol, we use SFT or DPO to suppress an unwanted existing model capability and then use ICL to try to bring that capability back (many-shot jailbreaking). We then study ICL on real-world instruction-tuned LLMs using capabilities benchmarks as well as a new many-shot jailbreaking dataset. In all cases, Bayesian scaling laws accurately predict the conditions under which ICL will cause suppressed behaviors to reemerge, which sheds light on the ineffectiveness of post-training at increasing LLM safety.

cs.CL↗

arXiv2025

Improved Representation Steering for Language Models

Steering methods for language models (LMs) seek to provide fine-grained and interpretable control over model generations by variously changing model inputs, weights, or representations to adjust behavior. Recent work has shown that adjusting weights or representations is often less effective than steering by prompting, for instance when wanting to introduce or suppress a particular concept. We demonstrate how to improve representation steering via our new Reference-free Preference Steering (RePS), a bidirectional preference-optimization objective that jointly does concept steering and suppression. We train three parameterizations of RePS and evaluate them on AxBench, a large-scale model steering benchmark. On Gemma models with sizes ranging from 2B to 27B, RePS outperforms all existing steering methods trained with a language modeling objective and substantially narrows the gap with prompting -- while promoting interpretability and minimizing parameter count. In suppression, RePS matches the language-modeling objective on Gemma-2 and outperforms it on the larger Gemma-3 variants while remaining resilient to prompt-based jailbreaking attacks that defeat prompting. Overall, our results suggest that RePS provides an interpretable and robust alternative to prompting for both steering and suppression.

cs.CL↗

arXiv2025

Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability

Causal abstraction provides a theoretical foundation for mechanistic interpretability, the field concerned with providing intelligible algorithms that are faithful simplifications of the known, but opaque low-level details of black box AI models. Our contributions are (1) generalizing the theory of causal abstraction from mechanism replacement (i.e., hard and soft interventions) to arbitrary mechanism transformation (i.e., functionals from old mechanisms to new mechanisms), (2) providing a flexible, yet precise formalization for the core concepts of polysemantic neurons, the linear representation hypothesis, modular features, and graded faithfulness, and (3) unifying a variety of mechanistic interpretability methods in the common language of causal abstraction, namely, activation and path patching, causal mediation analysis, causal scrubbing, causal tracing, circuit analysis, concept erasure, sparse autoencoders, differential binary masking, distributed alignment search, and steering.

cs.AI↗

arXiv2025

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based techniques as well, including sparse autoencoders (SAEs), linear artificial tomography, supervised steering vectors, linear probes, and representation finetuning. At present, there is no benchmark for making direct comparisons between these proposals. Therefore, we introduce AxBench, a large-scale benchmark for steering and concept detection, and report experiments on Gemma-2-2B and 9B. For steering, we find that prompting outperforms all existing methods, followed by finetuning. For concept detection, representation-based methods such as difference-in-means, perform the best. On both evaluations, SAEs are not competitive. We introduce a novel weakly-supervised representational method (Rank-1 Representation Finetuning; ReFT-r1), which is competitive on both tasks while providing the interpretability advantages that prompting lacks. Along with AxBench, we train and publicly release SAE-scale feature dictionaries for ReFT-r1 and DiffMean.

cs.CL↗

arXiv2024

ReFT: Representation Finetuning for Language Models

Parameter-efficient finetuning (PEFT) methods seek to adapt large neural models via updates to a small number of weights. However, much prior interpretability work has shown that representations encode rich semantic information, suggesting that editing representations might be a more powerful alternative. We pursue this hypothesis by developing a family of Representation Finetuning (ReFT) methods. ReFT methods operate on a frozen base model and learn task-specific interventions on hidden representations. We define a strong instance of the ReFT family, Low-rank Linear Subspace ReFT (LoReFT), and we identify an ablation of this method that trades some performance for increased efficiency. Both are drop-in replacements for existing PEFTs and learn interventions that are 15x--65x more parameter-efficient than LoRA. We showcase LoReFT on eight commonsense reasoning tasks, four arithmetic reasoning tasks, instruction-tuning, and GLUE. In all these evaluations, our ReFTs deliver the best balance of efficiency and performance, and almost always outperform state-of-the-art PEFTs. We release a generic ReFT training library publicly at https://github.com/stanfordnlp/pyreft.

cs.CL↗

arXiv2024

pyvene: A Library for Understanding and Improving PyTorch Models via Interventions

Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability. To facilitate such research, we introduce $\textbf{pyvene}$, an open-source Python library that supports customizable interventions on a range of different PyTorch modules. $\textbf{pyvene}$ supports complex intervention schemes with an intuitive configuration format, and its interventions can be static or include trainable parameters. We show how $\textbf{pyvene}$ provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others. We illustrate the power of the library via interpretability analyses using causal abstraction and knowledge localization. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at https://github.com/stanfordnlp/pyvene.

cs.LG↗

arXiv2024

CausalGym: Benchmarking causal interpretability methods on linguistic tasks

Language models (LMs) have proven to be powerful tools for psycholinguistic research, but most prior work has focused on purely behavioural measures (e.g., surprisal comparisons). At the same time, research in model interpretability has begun to illuminate the abstract causal mechanisms shaping LM behavior. To help bring these strands of research closer together, we introduce CausalGym. We adapt and expand the SyntaxGym suite of tasks to benchmark the ability of interpretability methods to causally affect model behaviour. To illustrate how CausalGym can be used, we study the pythia models (14M--6.9B) and assess the causal efficacy of a wide range of interpretability methods, including linear probing and distributed alignment search (DAS). We find that DAS outperforms the other methods, and so we use it to study the learning trajectory of two difficult linguistic phenomena in pythia-1b: negative polarity item licensing and filler--gap dependencies. Our analysis shows that the mechanism implementing both of these tasks is learned in discrete stages, not gradually.

cs.CL↗

arXiv2024

Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens

While massively multilingual speech models like wav2vec 2.0 XLSR-128 can be directly fine-tuned for automatic speech recognition (ASR), downstream performance can still be relatively poor on languages that are under-represented in the pre-training data. Continued pre-training on 70-200 hours of untranscribed speech in these languages can help -- but what about languages without that much recorded data? For such cases, we show that supplementing the target language with data from a similar, higher-resource 'donor' language can help. For example, continued pre-training on only 10 hours of low-resource Punjabi supplemented with 60 hours of donor Hindi is almost as good as continued pretraining on 70 hours of Punjabi. By contrast, sourcing data from less similar donors like Bengali does not improve ASR performance. To inform donor language selection, we propose a novel similarity metric based on the sequence distribution of induced acoustic units: the Acoustic Token Distribution Similarity (ATDS). Across a set of typologically different target languages (Punjabi, Galician, Iban, Setswana), we show that the ATDS between the target language and its candidate donors precisely predicts target language ASR performance.

eess.AS↗

arXiv2024

A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments

We respond to the recent paper by Makelov et al. (2023), which reviews subspace interchange intervention methods like distributed alignment search (DAS; Geiger et al. 2023) and claims that these methods potentially cause "interpretability illusions". We first review Makelov et al. (2023)'s technical notion of what an "interpretability illusion" is, and then we show that even intuitive and desirable explanations can qualify as illusions in this sense. As a result, their method of discovering "illusions" can reject explanations they consider "non-illusory". We then argue that the illusions Makelov et al. (2023) see in practice are artifacts of their training and evaluation paradigms. We close by emphasizing that, though we disagree with their core characterization, Makelov et al. (2023)'s examples and discussion have undoubtedly pushed the field of interpretability forward.

cs.LG↗

arXiv2023

IruMozhi: Automatically classifying diglossia in Tamil

Tamil, a Dravidian language of South Asia, is a highly diglossic language with two very different registers in everyday use: Literary Tamil (preferred in writing and formal communication) and Spoken Tamil (confined to speech and informal media). Spoken Tamil is under-supported in modern NLP systems. In this paper, we release IruMozhi, a human-annotated dataset of parallel text in Literary and Spoken Tamil. We train classifiers on the task of identifying which variety a text belongs to. We use these models to gauge the availability of pretraining data in Spoken Tamil, to audit the composition of existing labelled datasets for Tamil, and to encourage future work on the variety.

cs.CL↗

arXiv2023

Bhasacitra: Visualising the dialect geography of South Asia

We present Bhasacitra, a dialect mapping system for South Asia built on a database of linguistic studies of languages of the region annotated for topic and location data. We analyse language coverage and look towards applications to typology by visualising example datasets. The application is not only meant to be useful for feature mapping, but also serves as a new kind of interactive bibliography for linguists of South Asian languages.

cs.CL↗