arXiv subjects

Jayadev Billa

Publications and source records attributed to Jayadev Billa.

9 recordsLinked to original sources

arXiv2026

Decomposing the Depth Profile of Fine-Tuning

Fine-tuning adapts pretrained networks to new objectives. Whether the resulting depth profile of representational change reflects an intrinsic property of the model or the magnitude of gradient flow has not been tested directly. We measure this profile across 240 fine-tuning runs spanning 15 models in four architecture families (encoder and decoder transformers, a state-space model, and an RNN) at scales from 125M to 6.9B parameters. Representational change concentrates in output-proximal layers in every standard-training run except one. We apply a per-layer control that equalizes $\|\Delta W\|/\|W\|$ across layers after each optimizer step. Under this control, the profile persists in some conditions and collapses in others. At 125M--350M, sequential-block architectures (BERT, OPT, GPT-2) retain the slope across tested objectives while parallel-block architectures (Pythia, CodeGen) retain it only for causal-language-modeling objectives. This architectural distinction narrows at 1.3B--1.4B, where both block types show positive equal-step slopes for CausalLM. Under standard training, profile shape is described by two additional axes: steepness tracks a training-free objective distance at initialization, and profile width is dominated by architecture. We treat the locality gradient, the depthwise slope of representational change, as a composite phenomenon whose components are scale-dependent.

cs.LG↗

arXiv2026

Predicting Where Steering Vectors Succeed

Steering vectors work for some concepts and layers but fail for others, and practitioners have no way to predict which setting applies before running an intervention. We introduce the Linear Accessibility Profile (LAP), a per-layer diagnostic that repurposes the logit lens as a predictor of steering vector effectiveness. The key measure, $A_{\mathrm{lin}}$, applies the model's unembedding matrix to intermediate hidden states, requiring no training. Across 24 controlled binary concept families on five models (Pythia-2.8B to Llama-8B), peak $A_{\mathrm{lin}}$ predicts steering effectiveness at $\rho = +0.86$ to $+0.91$ and layer selection at $\rho = +0.63$ to $+0.92$. A three-regime framework explains when difference-of-means steering works, when nonlinear methods are needed, and when no method can work. An entity-steering demo confirms the prediction end-to-end: steering at the LAP-recommended layer redirects completions on Gemma-2-2B and OLMo-2-1B-Instruct, while the middle layer (the standard heuristic) has no effect on either model.

cs.LG↗

arXiv2026

Modality Collapse as Mismatched Decoding: Information-Theoretic Limits of Multimodal LLMs

Numerous studies have shown that multimodal LLMs process speech and images well but fail in non-intuitive ways rendering trivial tasks such as object counting unreliable. We investigate this behavior from an information-theoretic perspective by framing multimodal LLM inference as a mismatched decoder problem: a decoder trained primarily on text can only extract information along text-aligned directions (removing up to 98% of the variation in modality-specific (non-text) directions improves decoder loss) and the amount of accessible information is bounded by the Generalized Mutual Information (GMI). We show that information loss is bounded as the distributional mismatch between the source data and the text data increases, and as the sensitivity of the decoder increases. This bound is a function of the model's scoring rule not its architecture. We validate the predictions across five models spanning speech and vision. A controlled study (two Prismatic VLMs differing only in encoder text-alignment) shows that the bottleneck lies in the scoring rule of the decoder rather than the text-alignment of the encoder or the learned projection. A LoRA intervention demonstrates that simply training with an emotion-related objective improves emotion detection from 17.3% to 61.8% task accuracy without affecting other attributes, confirming that the training objective determines what becomes accessible.

cs.CL↗

arXiv2026

The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\rightarrow$LLM Pipelines?

Speech LLMs are widely understood to be better than ASR$\rightarrow$LLM cascades since they have access to the audio directly, and not just the transcript. In this paper, we present an evaluation methodology and a mechanistic interpretation of the observed behavior of speech LLMs. First, we introduce matched-backbone testing which separates out the behavior of the speech LLM from the reasoning capabilities of the underlying LLM. Second, we provide a mechanistic analysis of speech LLMs using logit lens and LEACE and show the literal transcript emerging from the LLM's hidden states and that text representations are causally necessary. We also show that in most deployed use cases, current speech LLMs are expensive cascades, and under noise, they are worse ones, with clean-condition advantages reversing by up to 7.6% at 0dB.

cs.CL↗

arXiv2026

The Geometric Anatomy of Capability Acquisition in Transformers

Neural networks gain capabilities during training, but the internal changes that precede capability acquisition are not well understood. In particular, the relationship between geometric change and behavioral change, and the effect of task difficulty and model scale on that relationship, is unclear. We track geometric measures and linear probes across six transformer sizes (405K--151M parameters), eight algorithmic tasks (144 task$\times$level$\times$model combinations), and three Pythia language models (160M--2.8B). Across all settings, representations first collapse to a low-dimensional state, then recover, and only then does behavioral performance improve. Linear probes show that the model's hidden states already contain task-relevant information before the model can act on it. The collapse floor is task-specific, the collapse propagates top-down through the network, and of the geometric measures tested, only \rankme reliably precedes capability acquisition for hard tasks. Whether this precursor is detectable depends on task difficulty relative to model capacity. For hard tasks, there is a clear gap: geometry changes first, behavior follows. For easy tasks, the model learns so quickly that both happen simultaneously and no precursor is detectable. On Pythia-2.8B, a logical deduction task that is genuinely hard for the model shows a precursor gap of ${\sim}$49K training steps, while easy benchmarks show none. This suggests that geometric patterns observed in small proxy models can persist at larger scale when the task remains difficult relative to model capacity.

cs.LG↗

arXiv2026

When Audio-LLMs Don't Listen: A Cross-Linguistic Study of Modality Arbitration

When audio and text conflict, speech-enabled language models follow text far more often than they do when arbitrating between two conflicting text sources, even under explicit instructions to trust the audio. We introduce ALME (Audio-LLM Modality Evaluation), a dataset of 57,602 controlled audio-text conflict stimuli across eight languages, together with Text Dominance Ratio (TDR), which measures how often a model follows conflicting text when instructed to follow audio. Gemini 2.0 Flash and GPT-4o show TDR 10--26$\times$ higher than a baseline that replaces audio with its transcript under otherwise identical conditions (Gemini 2.0 Flash: 16.6% vs. 1.6%; GPT-4o: 23.2% vs. 0.9%). These results suggest that text dominance reflects not only information content, but also an asymmetry in arbitration accessibility, i.e., how easily the model can use competing representations at decision time. Framing the transcript as deliberately corrupted reduces TDR by 80%, whereas forcing explicit transcription increases it by 14%. A fine-tuning ablation further suggests that arbitration behavior depends more on LLM reasoning than on the audio input path alone. Across four audio-LLMs, we observe the same qualitative pattern with substantial cross-model and cross-linguistic variation.

cs.CL↗

arXiv2022

Improving Low-Resource Speech Recognition with Pretrained Speech Models: Continued Pretraining vs. Semi-Supervised Training

Self-supervised Transformer based models, such as wav2vec 2.0 and HuBERT, have produced significant improvements over existing approaches to automatic speech recognition (ASR). This is evident in the performance of the wav2vec 2.0 based pretrained XLSR-53 model across many languages when fine-tuned with available labeled data. However, the performance from finetuning these models can be dependent on the amount of in-language or similar-to-in-language data included in the pretraining dataset. In this paper we investigate continued pretraining (CoPT) with unlabeled in-language audio data on the XLSR-53 pretrained model in several low-resource languages. CoPT is more computationally efficient than semi-supervised training (SST), the standard approach of utilizing unlabeled data in ASR, since it omits the need for pseudo-labeling of the unlabeled data. We show CoPT results in word error rates (WERs), equal to or slightly better than using SST. In addition, we show that using the CoPT model for pseudo-labeling, and using these labels in SST, results in further improvements in WER.

cs.CL↗

arXiv2021

Improving low-resource ASR performance with untranscribed out-of-domain data

Semi-supervised training (SST) is a common approach to leverage untranscribed/unlabeled speech data to improve automatic speech recognition performance in low-resource languages. However, if the available unlabeled speech is mismatched to the target domain, SST is not as effective, and in many cases performs worse than the original system. In this paper, we address the issue of low-resource ASR when only untranscribed out-of-domain speech data is readily available in the target language. Specifically, we look to improve performance on conversational/telephony speech (target domain) using web resources, in particular YouTube data, which more closely resembles news/topical broadcast data. Leveraging SST, we show that while in some cases simply pooling the out-of-domain data with the training data lowers word error rate (WER), in all cases, we see improvements if we train first with the out-of-domain data and then fine-tune the resulting model with the original training data. Using 2000 hours of speed perturbed YouTube audio in each target language, with semi-supervised transcripts, we show improvements on multiple languages/data sets, of up to 16.3% relative improvement in WER over the baseline systems and up to 7.4% relative improvement in WER over a system that simply pools the out-of-domain data with the training data.

cs.CL↗

arXiv2018

Improving LSTM-CTC based ASR performance in domains with limited training data

This paper addresses the observed performance gap between automatic speech recognition (ASR) systems based on Long Short Term Memory (LSTM) neural networks trained with the connectionist temporal classification (CTC) loss function and systems based on hybrid Deep Neural Networks (DNNs) trained with the cross entropy (CE) loss function on domains with limited data. We step through a number of experiments that show incremental improvements on a baseline EESEN toolkit based LSTM-CTC ASR system trained on the Librispeech 100hr (train-clean-100) corpus. Our results show that with effective combination of data augmentation and regularization, a LSTM-CTC based system can exceed the performance of a strong Kaldi based baseline trained on the same data.

cs.CL↗